diff --git a/checkpoint-1000/added_tokens.json b/checkpoint-1000/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..cd5b477a9075c49d99de65622db37bb06a251985
--- /dev/null
+++ b/checkpoint-1000/added_tokens.json
@@ -0,0 +1,4 @@
+{
+  "<ctc_blank>": 80,
+  "<mask>": 79
+}
diff --git a/checkpoint-1000/config.json b/checkpoint-1000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..778ad24a356630d39cc083e2d1df5699c25c0278
--- /dev/null
+++ b/checkpoint-1000/config.json
@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "microsoft/speecht5_tts",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SpeechT5ForTextToSpeech"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.1,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.1,
+  "encoder_layers": 12,
+  "encoder_max_relative_position": 160,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "guided_attention_loss_num_heads": 2,
+  "guided_attention_loss_scale": 10.0,
+  "guided_attention_loss_sigma": 0.4,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": null,
+  "max_speech_positions": 1876,
+  "max_text_positions": 600,
+  "model_type": "speecht5",
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_mel_bins": 80,
+  "pad_token_id": 1,
+  "positional_dropout": 0.1,
+  "reduction_factor": 2,
+  "scale_embedding": false,
+  "speaker_embedding_dim": 512,
+  "speech_decoder_postnet_dropout": 0.5,
+  "speech_decoder_postnet_kernel": 5,
+  "speech_decoder_postnet_layers": 5,
+  "speech_decoder_postnet_units": 256,
+  "speech_decoder_prenet_dropout": 0.5,
+  "speech_decoder_prenet_layers": 2,
+  "speech_decoder_prenet_units": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_guided_attention_loss": true,
+  "vocab_size": 81
+}
diff --git a/checkpoint-1000/generation_config.json b/checkpoint-1000/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5c3f497ae3f531fba6f7d3d8ed048ed02f110db1
--- /dev/null
+++ b/checkpoint-1000/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 1876,
+  "pad_token_id": 1,
+  "transformers_version": "4.46.1"
+}
diff --git a/checkpoint-1000/model.safetensors b/checkpoint-1000/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d31e7b60aaec4c7e4ec00eca9141320ab11071b2
--- /dev/null
+++ b/checkpoint-1000/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c5523d209511a8128afd892203133c6ff25481d87762c85914ce2373695e897
+size 577789320
diff --git a/checkpoint-1000/optimizer.pt b/checkpoint-1000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4cb56c601ee8e48fc283d9d96ebc895f140566c4
--- /dev/null
+++ b/checkpoint-1000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd0235c19281a1a11ce8bc188dc413063516990b69e039acfa1d4d10d9c91760
+size 1155772233
diff --git a/checkpoint-1000/preprocessor_config.json b/checkpoint-1000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..98a41e66e16f3225a15cb2b51c963fe2213aa273
--- /dev/null
+++ b/checkpoint-1000/preprocessor_config.json
@@ -0,0 +1,19 @@
+{
+  "do_normalize": false,
+  "feature_extractor_type": "SpeechT5FeatureExtractor",
+  "feature_size": 1,
+  "fmax": 7600,
+  "fmin": 80,
+  "frame_signal_scale": 1.0,
+  "hop_length": 16,
+  "mel_floor": 1e-10,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "SpeechT5Processor",
+  "reduction_factor": 2,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "win_function": "hann_window",
+  "win_length": 64
+}
diff --git a/checkpoint-1000/rng_state.pth b/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..44a6c090a174fe86e7d1cb956876fa0ead6f38e0
--- /dev/null
+++ b/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2391edd5840a83f113162293c889574d0eab13eb0642f28aae70d752ea782ed
+size 14244
diff --git a/checkpoint-1000/scheduler.pt b/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8565d90824cdbfd2ca3a73025f401c07d39317db
--- /dev/null
+++ b/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5101d8c1f86d6f48167e50b1164b9ba363ab76694ff2d5c1e326e3d5f94ecaef
+size 1064
diff --git a/checkpoint-1000/special_tokens_map.json b/checkpoint-1000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..4ee24ec69861cfc94abbe2c8c934aa0744aa623c
--- /dev/null
+++ b/checkpoint-1000/special_tokens_map.json
@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-1000/spm_char.model b/checkpoint-1000/spm_char.model
new file mode 100644
index 0000000000000000000000000000000000000000..8fb73691942626fa75df80b61aab0e9b9340d8e2
--- /dev/null
+++ b/checkpoint-1000/spm_char.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
+size 238473
diff --git a/checkpoint-1000/tokenizer_config.json b/checkpoint-1000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e8051ebd375d3357ac7b85aa5ba2982c351b423b
--- /dev/null
+++ b/checkpoint-1000/tokenizer_config.json
@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<ctc_blank>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 600,
+  "normalize": false,
+  "pad_token": "<pad>",
+  "processor_class": "SpeechT5Processor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "SpeechT5Tokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-1000/trainer_state.json b/checkpoint-1000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..014edc3bc527e3be9126ba9e0d430d544bce11c0
--- /dev/null
+++ b/checkpoint-1000/trainer_state.json
@@ -0,0 +1,321 @@
+{
+  "best_metric": 0.46117448806762695,
+  "best_model_checkpoint": "speecht5_finetuned_voxpopuli_pl/checkpoint-1000",
+  "epoch": 5.025125628140704,
+  "eval_steps": 1000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12562814070351758,
+      "grad_norm": 34.14754104614258,
+      "learning_rate": 4.6000000000000004e-07,
+      "loss": 6.2754,
+      "step": 25
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 25.906333923339844,
+      "learning_rate": 9.400000000000001e-07,
+      "loss": 6.1497,
+      "step": 50
+    },
+    {
+      "epoch": 0.3768844221105528,
+      "grad_norm": 29.097463607788086,
+      "learning_rate": 1.44e-06,
+      "loss": 6.0335,
+      "step": 75
+    },
+    {
+      "epoch": 0.5025125628140703,
+      "grad_norm": 18.543378829956055,
+      "learning_rate": 1.94e-06,
+      "loss": 5.8815,
+      "step": 100
+    },
+    {
+      "epoch": 0.628140703517588,
+      "grad_norm": 24.147188186645508,
+      "learning_rate": 2.4400000000000004e-06,
+      "loss": 5.5659,
+      "step": 125
+    },
+    {
+      "epoch": 0.7537688442211056,
+      "grad_norm": 15.634539604187012,
+      "learning_rate": 2.9400000000000002e-06,
+      "loss": 5.3573,
+      "step": 150
+    },
+    {
+      "epoch": 0.8793969849246231,
+      "grad_norm": 14.31460189819336,
+      "learning_rate": 3.44e-06,
+      "loss": 5.2616,
+      "step": 175
+    },
+    {
+      "epoch": 1.0050251256281406,
+      "grad_norm": 19.75978660583496,
+      "learning_rate": 3.94e-06,
+      "loss": 5.1787,
+      "step": 200
+    },
+    {
+      "epoch": 1.1306532663316582,
+      "grad_norm": 12.639854431152344,
+      "learning_rate": 4.440000000000001e-06,
+      "loss": 5.1214,
+      "step": 225
+    },
+    {
+      "epoch": 1.2562814070351758,
+      "grad_norm": 17.792396545410156,
+      "learning_rate": 4.94e-06,
+      "loss": 5.0703,
+      "step": 250
+    },
+    {
+      "epoch": 1.3819095477386933,
+      "grad_norm": 22.859201431274414,
+      "learning_rate": 5.4400000000000004e-06,
+      "loss": 4.9714,
+      "step": 275
+    },
+    {
+      "epoch": 1.507537688442211,
+      "grad_norm": 16.62458610534668,
+      "learning_rate": 5.94e-06,
+      "loss": 4.8681,
+      "step": 300
+    },
+    {
+      "epoch": 1.6331658291457285,
+      "grad_norm": 17.881174087524414,
+      "learning_rate": 6.440000000000001e-06,
+      "loss": 4.8252,
+      "step": 325
+    },
+    {
+      "epoch": 1.758793969849246,
+      "grad_norm": 14.765595436096191,
+      "learning_rate": 6.9400000000000005e-06,
+      "loss": 4.5588,
+      "step": 350
+    },
+    {
+      "epoch": 1.8844221105527639,
+      "grad_norm": 13.808978080749512,
+      "learning_rate": 7.440000000000001e-06,
+      "loss": 4.5211,
+      "step": 375
+    },
+    {
+      "epoch": 2.0100502512562812,
+      "grad_norm": 10.674385070800781,
+      "learning_rate": 7.94e-06,
+      "loss": 4.4888,
+      "step": 400
+    },
+    {
+      "epoch": 2.135678391959799,
+      "grad_norm": 15.555588722229004,
+      "learning_rate": 8.44e-06,
+      "loss": 4.4513,
+      "step": 425
+    },
+    {
+      "epoch": 2.2613065326633164,
+      "grad_norm": 13.092530250549316,
+      "learning_rate": 8.94e-06,
+      "loss": 4.3646,
+      "step": 450
+    },
+    {
+      "epoch": 2.3869346733668344,
+      "grad_norm": 12.971352577209473,
+      "learning_rate": 9.440000000000001e-06,
+      "loss": 4.3459,
+      "step": 475
+    },
+    {
+      "epoch": 2.5125628140703515,
+      "grad_norm": 10.348517417907715,
+      "learning_rate": 9.940000000000001e-06,
+      "loss": 4.2915,
+      "step": 500
+    },
+    {
+      "epoch": 2.6381909547738696,
+      "grad_norm": 13.625853538513184,
+      "learning_rate": 9.937142857142858e-06,
+      "loss": 4.3095,
+      "step": 525
+    },
+    {
+      "epoch": 2.7638190954773867,
+      "grad_norm": 11.426923751831055,
+      "learning_rate": 9.865714285714285e-06,
+      "loss": 4.1899,
+      "step": 550
+    },
+    {
+      "epoch": 2.8894472361809047,
+      "grad_norm": 11.516312599182129,
+      "learning_rate": 9.794285714285714e-06,
+      "loss": 4.2233,
+      "step": 575
+    },
+    {
+      "epoch": 3.0150753768844223,
+      "grad_norm": 16.141698837280273,
+      "learning_rate": 9.722857142857143e-06,
+      "loss": 4.1831,
+      "step": 600
+    },
+    {
+      "epoch": 3.14070351758794,
+      "grad_norm": 14.935202598571777,
+      "learning_rate": 9.651428571428572e-06,
+      "loss": 4.1739,
+      "step": 625
+    },
+    {
+      "epoch": 3.2663316582914574,
+      "grad_norm": 10.119762420654297,
+      "learning_rate": 9.58e-06,
+      "loss": 4.1649,
+      "step": 650
+    },
+    {
+      "epoch": 3.391959798994975,
+      "grad_norm": 16.50948143005371,
+      "learning_rate": 9.508571428571429e-06,
+      "loss": 4.1627,
+      "step": 675
+    },
+    {
+      "epoch": 3.5175879396984926,
+      "grad_norm": 10.08300495147705,
+      "learning_rate": 9.437142857142858e-06,
+      "loss": 4.1915,
+      "step": 700
+    },
+    {
+      "epoch": 3.64321608040201,
+      "grad_norm": 9.375288963317871,
+      "learning_rate": 9.365714285714287e-06,
+      "loss": 4.1279,
+      "step": 725
+    },
+    {
+      "epoch": 3.7688442211055277,
+      "grad_norm": 13.562234878540039,
+      "learning_rate": 9.294285714285714e-06,
+      "loss": 4.1083,
+      "step": 750
+    },
+    {
+      "epoch": 3.8944723618090453,
+      "grad_norm": 15.115653991699219,
+      "learning_rate": 9.222857142857143e-06,
+      "loss": 4.1236,
+      "step": 775
+    },
+    {
+      "epoch": 4.0201005025125625,
+      "grad_norm": 9.049237251281738,
+      "learning_rate": 9.151428571428572e-06,
+      "loss": 4.0964,
+      "step": 800
+    },
+    {
+      "epoch": 4.1457286432160805,
+      "grad_norm": 9.250771522521973,
+      "learning_rate": 9.080000000000001e-06,
+      "loss": 4.0669,
+      "step": 825
+    },
+    {
+      "epoch": 4.271356783919598,
+      "grad_norm": 12.07302474975586,
+      "learning_rate": 9.00857142857143e-06,
+      "loss": 4.0587,
+      "step": 850
+    },
+    {
+      "epoch": 4.396984924623116,
+      "grad_norm": 9.538933753967285,
+      "learning_rate": 8.937142857142857e-06,
+      "loss": 4.0837,
+      "step": 875
+    },
+    {
+      "epoch": 4.522613065326633,
+      "grad_norm": 14.347626686096191,
+      "learning_rate": 8.865714285714287e-06,
+      "loss": 4.0086,
+      "step": 900
+    },
+    {
+      "epoch": 4.648241206030151,
+      "grad_norm": 10.831369400024414,
+      "learning_rate": 8.794285714285716e-06,
+      "loss": 4.0563,
+      "step": 925
+    },
+    {
+      "epoch": 4.773869346733669,
+      "grad_norm": 9.891343116760254,
+      "learning_rate": 8.722857142857145e-06,
+      "loss": 4.0057,
+      "step": 950
+    },
+    {
+      "epoch": 4.899497487437186,
+      "grad_norm": 9.572471618652344,
+      "learning_rate": 8.651428571428572e-06,
+      "loss": 4.0557,
+      "step": 975
+    },
+    {
+      "epoch": 5.025125628140704,
+      "grad_norm": 9.745298385620117,
+      "learning_rate": 8.580000000000001e-06,
+      "loss": 3.9902,
+      "step": 1000
+    },
+    {
+      "epoch": 5.025125628140704,
+      "eval_loss": 0.46117448806762695,
+      "eval_runtime": 75.4681,
+      "eval_samples_per_second": 9.381,
+      "eval_steps_per_second": 4.691,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 21,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4502414650961304.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1000/training_args.bin b/checkpoint-1000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6ccf0404925f6a8a3bda1ade1cb95630a3b1750a
--- /dev/null
+++ b/checkpoint-1000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6ae756af4eb40168228ea5b672dedd9146f11deae4f8d64668e0b2d5a69781
+size 5432
diff --git a/checkpoint-2000/added_tokens.json b/checkpoint-2000/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..cd5b477a9075c49d99de65622db37bb06a251985
--- /dev/null
+++ b/checkpoint-2000/added_tokens.json
@@ -0,0 +1,4 @@
+{
+  "<ctc_blank>": 80,
+  "<mask>": 79
+}
diff --git a/checkpoint-2000/config.json b/checkpoint-2000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..778ad24a356630d39cc083e2d1df5699c25c0278
--- /dev/null
+++ b/checkpoint-2000/config.json
@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "microsoft/speecht5_tts",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SpeechT5ForTextToSpeech"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.1,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.1,
+  "encoder_layers": 12,
+  "encoder_max_relative_position": 160,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "guided_attention_loss_num_heads": 2,
+  "guided_attention_loss_scale": 10.0,
+  "guided_attention_loss_sigma": 0.4,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": null,
+  "max_speech_positions": 1876,
+  "max_text_positions": 600,
+  "model_type": "speecht5",
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_mel_bins": 80,
+  "pad_token_id": 1,
+  "positional_dropout": 0.1,
+  "reduction_factor": 2,
+  "scale_embedding": false,
+  "speaker_embedding_dim": 512,
+  "speech_decoder_postnet_dropout": 0.5,
+  "speech_decoder_postnet_kernel": 5,
+  "speech_decoder_postnet_layers": 5,
+  "speech_decoder_postnet_units": 256,
+  "speech_decoder_prenet_dropout": 0.5,
+  "speech_decoder_prenet_layers": 2,
+  "speech_decoder_prenet_units": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_guided_attention_loss": true,
+  "vocab_size": 81
+}
diff --git a/checkpoint-2000/generation_config.json b/checkpoint-2000/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5c3f497ae3f531fba6f7d3d8ed048ed02f110db1
--- /dev/null
+++ b/checkpoint-2000/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 1876,
+  "pad_token_id": 1,
+  "transformers_version": "4.46.1"
+}
diff --git a/checkpoint-2000/model.safetensors b/checkpoint-2000/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6b6fa4ffa37745f93eba454dacc3cab87d9643f7
--- /dev/null
+++ b/checkpoint-2000/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df394cff2c937d31a29d6243ea8e3ebcc79a50d23be775a4fba7dd7734dd1582
+size 577789320
diff --git a/checkpoint-2000/optimizer.pt b/checkpoint-2000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9c853e63ede28863122eabf8b50e3f4620d556ad
--- /dev/null
+++ b/checkpoint-2000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c2f15b423ce9e08c24c5f007046f57b502016d95208dbd3b0962042f7351fb
+size 1155772233
diff --git a/checkpoint-2000/preprocessor_config.json b/checkpoint-2000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..98a41e66e16f3225a15cb2b51c963fe2213aa273
--- /dev/null
+++ b/checkpoint-2000/preprocessor_config.json
@@ -0,0 +1,19 @@
+{
+  "do_normalize": false,
+  "feature_extractor_type": "SpeechT5FeatureExtractor",
+  "feature_size": 1,
+  "fmax": 7600,
+  "fmin": 80,
+  "frame_signal_scale": 1.0,
+  "hop_length": 16,
+  "mel_floor": 1e-10,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "SpeechT5Processor",
+  "reduction_factor": 2,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "win_function": "hann_window",
+  "win_length": 64
+}
diff --git a/checkpoint-2000/rng_state.pth b/checkpoint-2000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..58ccf389019a11e4c48fa99d1bc456603dd8068a
--- /dev/null
+++ b/checkpoint-2000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3866dfdf0b13997fd63f79fbe98278f2ebe8e2dceb446d3d72314597efc00327
+size 14244
diff --git a/checkpoint-2000/scheduler.pt b/checkpoint-2000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2a6460a89462994303545a8f3997e58e1490360f
--- /dev/null
+++ b/checkpoint-2000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b80a609c64a12b4db2f38941ea479b9a30f9351b7aac74f4956e8686dc338317
+size 1064
diff --git a/checkpoint-2000/special_tokens_map.json b/checkpoint-2000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..4ee24ec69861cfc94abbe2c8c934aa0744aa623c
--- /dev/null
+++ b/checkpoint-2000/special_tokens_map.json
@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-2000/spm_char.model b/checkpoint-2000/spm_char.model
new file mode 100644
index 0000000000000000000000000000000000000000..8fb73691942626fa75df80b61aab0e9b9340d8e2
--- /dev/null
+++ b/checkpoint-2000/spm_char.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
+size 238473
diff --git a/checkpoint-2000/tokenizer_config.json b/checkpoint-2000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e8051ebd375d3357ac7b85aa5ba2982c351b423b
--- /dev/null
+++ b/checkpoint-2000/tokenizer_config.json
@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<ctc_blank>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 600,
+  "normalize": false,
+  "pad_token": "<pad>",
+  "processor_class": "SpeechT5Processor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "SpeechT5Tokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-2000/trainer_state.json b/checkpoint-2000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..3ed178944f671fbb8dd48ab60f2e91dbbdda3958
--- /dev/null
+++ b/checkpoint-2000/trainer_state.json
@@ -0,0 +1,609 @@
+{
+  "best_metric": 0.44917792081832886,
+  "best_model_checkpoint": "speecht5_finetuned_voxpopuli_pl/checkpoint-2000",
+  "epoch": 10.050251256281408,
+  "eval_steps": 1000,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12562814070351758,
+      "grad_norm": 34.14754104614258,
+      "learning_rate": 4.6000000000000004e-07,
+      "loss": 6.2754,
+      "step": 25
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 25.906333923339844,
+      "learning_rate": 9.400000000000001e-07,
+      "loss": 6.1497,
+      "step": 50
+    },
+    {
+      "epoch": 0.3768844221105528,
+      "grad_norm": 29.097463607788086,
+      "learning_rate": 1.44e-06,
+      "loss": 6.0335,
+      "step": 75
+    },
+    {
+      "epoch": 0.5025125628140703,
+      "grad_norm": 18.543378829956055,
+      "learning_rate": 1.94e-06,
+      "loss": 5.8815,
+      "step": 100
+    },
+    {
+      "epoch": 0.628140703517588,
+      "grad_norm": 24.147188186645508,
+      "learning_rate": 2.4400000000000004e-06,
+      "loss": 5.5659,
+      "step": 125
+    },
+    {
+      "epoch": 0.7537688442211056,
+      "grad_norm": 15.634539604187012,
+      "learning_rate": 2.9400000000000002e-06,
+      "loss": 5.3573,
+      "step": 150
+    },
+    {
+      "epoch": 0.8793969849246231,
+      "grad_norm": 14.31460189819336,
+      "learning_rate": 3.44e-06,
+      "loss": 5.2616,
+      "step": 175
+    },
+    {
+      "epoch": 1.0050251256281406,
+      "grad_norm": 19.75978660583496,
+      "learning_rate": 3.94e-06,
+      "loss": 5.1787,
+      "step": 200
+    },
+    {
+      "epoch": 1.1306532663316582,
+      "grad_norm": 12.639854431152344,
+      "learning_rate": 4.440000000000001e-06,
+      "loss": 5.1214,
+      "step": 225
+    },
+    {
+      "epoch": 1.2562814070351758,
+      "grad_norm": 17.792396545410156,
+      "learning_rate": 4.94e-06,
+      "loss": 5.0703,
+      "step": 250
+    },
+    {
+      "epoch": 1.3819095477386933,
+      "grad_norm": 22.859201431274414,
+      "learning_rate": 5.4400000000000004e-06,
+      "loss": 4.9714,
+      "step": 275
+    },
+    {
+      "epoch": 1.507537688442211,
+      "grad_norm": 16.62458610534668,
+      "learning_rate": 5.94e-06,
+      "loss": 4.8681,
+      "step": 300
+    },
+    {
+      "epoch": 1.6331658291457285,
+      "grad_norm": 17.881174087524414,
+      "learning_rate": 6.440000000000001e-06,
+      "loss": 4.8252,
+      "step": 325
+    },
+    {
+      "epoch": 1.758793969849246,
+      "grad_norm": 14.765595436096191,
+      "learning_rate": 6.9400000000000005e-06,
+      "loss": 4.5588,
+      "step": 350
+    },
+    {
+      "epoch": 1.8844221105527639,
+      "grad_norm": 13.808978080749512,
+      "learning_rate": 7.440000000000001e-06,
+      "loss": 4.5211,
+      "step": 375
+    },
+    {
+      "epoch": 2.0100502512562812,
+      "grad_norm": 10.674385070800781,
+      "learning_rate": 7.94e-06,
+      "loss": 4.4888,
+      "step": 400
+    },
+    {
+      "epoch": 2.135678391959799,
+      "grad_norm": 15.555588722229004,
+      "learning_rate": 8.44e-06,
+      "loss": 4.4513,
+      "step": 425
+    },
+    {
+      "epoch": 2.2613065326633164,
+      "grad_norm": 13.092530250549316,
+      "learning_rate": 8.94e-06,
+      "loss": 4.3646,
+      "step": 450
+    },
+    {
+      "epoch": 2.3869346733668344,
+      "grad_norm": 12.971352577209473,
+      "learning_rate": 9.440000000000001e-06,
+      "loss": 4.3459,
+      "step": 475
+    },
+    {
+      "epoch": 2.5125628140703515,
+      "grad_norm": 10.348517417907715,
+      "learning_rate": 9.940000000000001e-06,
+      "loss": 4.2915,
+      "step": 500
+    },
+    {
+      "epoch": 2.6381909547738696,
+      "grad_norm": 13.625853538513184,
+      "learning_rate": 9.937142857142858e-06,
+      "loss": 4.3095,
+      "step": 525
+    },
+    {
+      "epoch": 2.7638190954773867,
+      "grad_norm": 11.426923751831055,
+      "learning_rate": 9.865714285714285e-06,
+      "loss": 4.1899,
+      "step": 550
+    },
+    {
+      "epoch": 2.8894472361809047,
+      "grad_norm": 11.516312599182129,
+      "learning_rate": 9.794285714285714e-06,
+      "loss": 4.2233,
+      "step": 575
+    },
+    {
+      "epoch": 3.0150753768844223,
+      "grad_norm": 16.141698837280273,
+      "learning_rate": 9.722857142857143e-06,
+      "loss": 4.1831,
+      "step": 600
+    },
+    {
+      "epoch": 3.14070351758794,
+      "grad_norm": 14.935202598571777,
+      "learning_rate": 9.651428571428572e-06,
+      "loss": 4.1739,
+      "step": 625
+    },
+    {
+      "epoch": 3.2663316582914574,
+      "grad_norm": 10.119762420654297,
+      "learning_rate": 9.58e-06,
+      "loss": 4.1649,
+      "step": 650
+    },
+    {
+      "epoch": 3.391959798994975,
+      "grad_norm": 16.50948143005371,
+      "learning_rate": 9.508571428571429e-06,
+      "loss": 4.1627,
+      "step": 675
+    },
+    {
+      "epoch": 3.5175879396984926,
+      "grad_norm": 10.08300495147705,
+      "learning_rate": 9.437142857142858e-06,
+      "loss": 4.1915,
+      "step": 700
+    },
+    {
+      "epoch": 3.64321608040201,
+      "grad_norm": 9.375288963317871,
+      "learning_rate": 9.365714285714287e-06,
+      "loss": 4.1279,
+      "step": 725
+    },
+    {
+      "epoch": 3.7688442211055277,
+      "grad_norm": 13.562234878540039,
+      "learning_rate": 9.294285714285714e-06,
+      "loss": 4.1083,
+      "step": 750
+    },
+    {
+      "epoch": 3.8944723618090453,
+      "grad_norm": 15.115653991699219,
+      "learning_rate": 9.222857142857143e-06,
+      "loss": 4.1236,
+      "step": 775
+    },
+    {
+      "epoch": 4.0201005025125625,
+      "grad_norm": 9.049237251281738,
+      "learning_rate": 9.151428571428572e-06,
+      "loss": 4.0964,
+      "step": 800
+    },
+    {
+      "epoch": 4.1457286432160805,
+      "grad_norm": 9.250771522521973,
+      "learning_rate": 9.080000000000001e-06,
+      "loss": 4.0669,
+      "step": 825
+    },
+    {
+      "epoch": 4.271356783919598,
+      "grad_norm": 12.07302474975586,
+      "learning_rate": 9.00857142857143e-06,
+      "loss": 4.0587,
+      "step": 850
+    },
+    {
+      "epoch": 4.396984924623116,
+      "grad_norm": 9.538933753967285,
+      "learning_rate": 8.937142857142857e-06,
+      "loss": 4.0837,
+      "step": 875
+    },
+    {
+      "epoch": 4.522613065326633,
+      "grad_norm": 14.347626686096191,
+      "learning_rate": 8.865714285714287e-06,
+      "loss": 4.0086,
+      "step": 900
+    },
+    {
+      "epoch": 4.648241206030151,
+      "grad_norm": 10.831369400024414,
+      "learning_rate": 8.794285714285716e-06,
+      "loss": 4.0563,
+      "step": 925
+    },
+    {
+      "epoch": 4.773869346733669,
+      "grad_norm": 9.891343116760254,
+      "learning_rate": 8.722857142857145e-06,
+      "loss": 4.0057,
+      "step": 950
+    },
+    {
+      "epoch": 4.899497487437186,
+      "grad_norm": 9.572471618652344,
+      "learning_rate": 8.651428571428572e-06,
+      "loss": 4.0557,
+      "step": 975
+    },
+    {
+      "epoch": 5.025125628140704,
+      "grad_norm": 9.745298385620117,
+      "learning_rate": 8.580000000000001e-06,
+      "loss": 3.9902,
+      "step": 1000
+    },
+    {
+      "epoch": 5.025125628140704,
+      "eval_loss": 0.46117448806762695,
+      "eval_runtime": 75.4681,
+      "eval_samples_per_second": 9.381,
+      "eval_steps_per_second": 4.691,
+      "step": 1000
+    },
+    {
+      "epoch": 5.150753768844221,
+      "grad_norm": 10.219923973083496,
+      "learning_rate": 8.50857142857143e-06,
+      "loss": 3.9991,
+      "step": 1025
+    },
+    {
+      "epoch": 5.276381909547739,
+      "grad_norm": 9.258833885192871,
+      "learning_rate": 8.437142857142859e-06,
+      "loss": 4.0032,
+      "step": 1050
+    },
+    {
+      "epoch": 5.402010050251256,
+      "grad_norm": 12.21104907989502,
+      "learning_rate": 8.365714285714286e-06,
+      "loss": 4.0337,
+      "step": 1075
+    },
+    {
+      "epoch": 5.527638190954773,
+      "grad_norm": 10.777599334716797,
+      "learning_rate": 8.294285714285715e-06,
+      "loss": 4.0036,
+      "step": 1100
+    },
+    {
+      "epoch": 5.653266331658291,
+      "grad_norm": 10.322349548339844,
+      "learning_rate": 8.222857142857144e-06,
+      "loss": 3.9811,
+      "step": 1125
+    },
+    {
+      "epoch": 5.778894472361809,
+      "grad_norm": 9.940053939819336,
+      "learning_rate": 8.151428571428572e-06,
+      "loss": 4.0264,
+      "step": 1150
+    },
+    {
+      "epoch": 5.9045226130653266,
+      "grad_norm": 12.996850967407227,
+      "learning_rate": 8.08e-06,
+      "loss": 3.9783,
+      "step": 1175
+    },
+    {
+      "epoch": 6.030150753768845,
+      "grad_norm": 10.784270286560059,
+      "learning_rate": 8.00857142857143e-06,
+      "loss": 3.936,
+      "step": 1200
+    },
+    {
+      "epoch": 6.155778894472362,
+      "grad_norm": 10.86549186706543,
+      "learning_rate": 7.937142857142857e-06,
+      "loss": 3.9803,
+      "step": 1225
+    },
+    {
+      "epoch": 6.28140703517588,
+      "grad_norm": 10.926647186279297,
+      "learning_rate": 7.865714285714286e-06,
+      "loss": 3.9587,
+      "step": 1250
+    },
+    {
+      "epoch": 6.407035175879397,
+      "grad_norm": 12.103693008422852,
+      "learning_rate": 7.794285714285715e-06,
+      "loss": 3.9441,
+      "step": 1275
+    },
+    {
+      "epoch": 6.532663316582915,
+      "grad_norm": 14.731566429138184,
+      "learning_rate": 7.722857142857142e-06,
+      "loss": 3.9541,
+      "step": 1300
+    },
+    {
+      "epoch": 6.658291457286432,
+      "grad_norm": 13.810087203979492,
+      "learning_rate": 7.651428571428571e-06,
+      "loss": 3.962,
+      "step": 1325
+    },
+    {
+      "epoch": 6.78391959798995,
+      "grad_norm": 10.733597755432129,
+      "learning_rate": 7.58e-06,
+      "loss": 3.9696,
+      "step": 1350
+    },
+    {
+      "epoch": 6.909547738693467,
+      "grad_norm": 12.271906852722168,
+      "learning_rate": 7.508571428571429e-06,
+      "loss": 3.9319,
+      "step": 1375
+    },
+    {
+      "epoch": 7.035175879396985,
+      "grad_norm": 17.454214096069336,
+      "learning_rate": 7.4371428571428575e-06,
+      "loss": 3.9096,
+      "step": 1400
+    },
+    {
+      "epoch": 7.160804020100502,
+      "grad_norm": 9.891731262207031,
+      "learning_rate": 7.365714285714286e-06,
+      "loss": 3.963,
+      "step": 1425
+    },
+    {
+      "epoch": 7.28643216080402,
+      "grad_norm": 10.400883674621582,
+      "learning_rate": 7.294285714285715e-06,
+      "loss": 3.9529,
+      "step": 1450
+    },
+    {
+      "epoch": 7.4120603015075375,
+      "grad_norm": 8.886434555053711,
+      "learning_rate": 7.222857142857144e-06,
+      "loss": 3.9048,
+      "step": 1475
+    },
+    {
+      "epoch": 7.5376884422110555,
+      "grad_norm": 13.72711181640625,
+      "learning_rate": 7.151428571428573e-06,
+      "loss": 3.9097,
+      "step": 1500
+    },
+    {
+      "epoch": 7.663316582914573,
+      "grad_norm": 10.161803245544434,
+      "learning_rate": 7.08e-06,
+      "loss": 3.9029,
+      "step": 1525
+    },
+    {
+      "epoch": 7.788944723618091,
+      "grad_norm": 9.717086791992188,
+      "learning_rate": 7.008571428571429e-06,
+      "loss": 3.9028,
+      "step": 1550
+    },
+    {
+      "epoch": 7.914572864321608,
+      "grad_norm": 9.483698844909668,
+      "learning_rate": 6.937142857142858e-06,
+      "loss": 3.9157,
+      "step": 1575
+    },
+    {
+      "epoch": 8.040201005025125,
+      "grad_norm": 8.951908111572266,
+      "learning_rate": 6.865714285714287e-06,
+      "loss": 3.9106,
+      "step": 1600
+    },
+    {
+      "epoch": 8.165829145728644,
+      "grad_norm": 8.099654197692871,
+      "learning_rate": 6.794285714285714e-06,
+      "loss": 3.9062,
+      "step": 1625
+    },
+    {
+      "epoch": 8.291457286432161,
+      "grad_norm": 10.005452156066895,
+      "learning_rate": 6.722857142857143e-06,
+      "loss": 3.9139,
+      "step": 1650
+    },
+    {
+      "epoch": 8.417085427135678,
+      "grad_norm": 7.832030296325684,
+      "learning_rate": 6.651428571428572e-06,
+      "loss": 3.8731,
+      "step": 1675
+    },
+    {
+      "epoch": 8.542713567839195,
+      "grad_norm": 9.519272804260254,
+      "learning_rate": 6.5800000000000005e-06,
+      "loss": 3.9234,
+      "step": 1700
+    },
+    {
+      "epoch": 8.668341708542714,
+      "grad_norm": 7.6004252433776855,
+      "learning_rate": 6.5085714285714295e-06,
+      "loss": 3.8889,
+      "step": 1725
+    },
+    {
+      "epoch": 8.793969849246231,
+      "grad_norm": 8.43916130065918,
+      "learning_rate": 6.437142857142858e-06,
+      "loss": 3.8813,
+      "step": 1750
+    },
+    {
+      "epoch": 8.919597989949748,
+      "grad_norm": 9.573629379272461,
+      "learning_rate": 6.365714285714286e-06,
+      "loss": 3.9234,
+      "step": 1775
+    },
+    {
+      "epoch": 9.045226130653266,
+      "grad_norm": 11.034466743469238,
+      "learning_rate": 6.294285714285715e-06,
+      "loss": 3.9227,
+      "step": 1800
+    },
+    {
+      "epoch": 9.170854271356784,
+      "grad_norm": 9.65125560760498,
+      "learning_rate": 6.222857142857144e-06,
+      "loss": 3.8806,
+      "step": 1825
+    },
+    {
+      "epoch": 9.296482412060302,
+      "grad_norm": 8.907113075256348,
+      "learning_rate": 6.151428571428571e-06,
+      "loss": 3.8878,
+      "step": 1850
+    },
+    {
+      "epoch": 9.422110552763819,
+      "grad_norm": 9.000490188598633,
+      "learning_rate": 6.08e-06,
+      "loss": 3.858,
+      "step": 1875
+    },
+    {
+      "epoch": 9.547738693467338,
+      "grad_norm": 10.825636863708496,
+      "learning_rate": 6.008571428571429e-06,
+      "loss": 3.8546,
+      "step": 1900
+    },
+    {
+      "epoch": 9.673366834170855,
+      "grad_norm": 8.722935676574707,
+      "learning_rate": 5.937142857142858e-06,
+      "loss": 3.871,
+      "step": 1925
+    },
+    {
+      "epoch": 9.798994974874372,
+      "grad_norm": 9.243980407714844,
+      "learning_rate": 5.865714285714286e-06,
+      "loss": 3.8486,
+      "step": 1950
+    },
+    {
+      "epoch": 9.924623115577889,
+      "grad_norm": 10.595390319824219,
+      "learning_rate": 5.794285714285715e-06,
+      "loss": 3.8973,
+      "step": 1975
+    },
+    {
+      "epoch": 10.050251256281408,
+      "grad_norm": 11.8334321975708,
+      "learning_rate": 5.722857142857144e-06,
+      "loss": 3.8124,
+      "step": 2000
+    },
+    {
+      "epoch": 10.050251256281408,
+      "eval_loss": 0.44917792081832886,
+      "eval_runtime": 76.9989,
+      "eval_samples_per_second": 9.195,
+      "eval_steps_per_second": 4.597,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 21,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9000871252452288.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2000/training_args.bin b/checkpoint-2000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6ccf0404925f6a8a3bda1ade1cb95630a3b1750a
--- /dev/null
+++ b/checkpoint-2000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6ae756af4eb40168228ea5b672dedd9146f11deae4f8d64668e0b2d5a69781
+size 5432
diff --git a/checkpoint-3000/added_tokens.json b/checkpoint-3000/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..cd5b477a9075c49d99de65622db37bb06a251985
--- /dev/null
+++ b/checkpoint-3000/added_tokens.json
@@ -0,0 +1,4 @@
+{
+  "<ctc_blank>": 80,
+  "<mask>": 79
+}
diff --git a/checkpoint-3000/config.json b/checkpoint-3000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..778ad24a356630d39cc083e2d1df5699c25c0278
--- /dev/null
+++ b/checkpoint-3000/config.json
@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "microsoft/speecht5_tts",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SpeechT5ForTextToSpeech"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.1,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.1,
+  "encoder_layers": 12,
+  "encoder_max_relative_position": 160,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "guided_attention_loss_num_heads": 2,
+  "guided_attention_loss_scale": 10.0,
+  "guided_attention_loss_sigma": 0.4,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": null,
+  "max_speech_positions": 1876,
+  "max_text_positions": 600,
+  "model_type": "speecht5",
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_mel_bins": 80,
+  "pad_token_id": 1,
+  "positional_dropout": 0.1,
+  "reduction_factor": 2,
+  "scale_embedding": false,
+  "speaker_embedding_dim": 512,
+  "speech_decoder_postnet_dropout": 0.5,
+  "speech_decoder_postnet_kernel": 5,
+  "speech_decoder_postnet_layers": 5,
+  "speech_decoder_postnet_units": 256,
+  "speech_decoder_prenet_dropout": 0.5,
+  "speech_decoder_prenet_layers": 2,
+  "speech_decoder_prenet_units": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_guided_attention_loss": true,
+  "vocab_size": 81
+}
diff --git a/checkpoint-3000/generation_config.json b/checkpoint-3000/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5c3f497ae3f531fba6f7d3d8ed048ed02f110db1
--- /dev/null
+++ b/checkpoint-3000/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 1876,
+  "pad_token_id": 1,
+  "transformers_version": "4.46.1"
+}
diff --git a/checkpoint-3000/model.safetensors b/checkpoint-3000/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5c7c11f106946a67fa571eaddb991433910990b6
--- /dev/null
+++ b/checkpoint-3000/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d626a5faf08be1905193f75162a4ec7b6f770ff4e9fa828e8b9ae33d56ed90
+size 577789320
diff --git a/checkpoint-3000/optimizer.pt b/checkpoint-3000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9b104bbaeddbf7b0788a49432ff4b0060f64c811
--- /dev/null
+++ b/checkpoint-3000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f763cc61d97cb2027a0997575ca0b715bc34ab7c43dbbf5e513f229b92fe081
+size 1155772233
diff --git a/checkpoint-3000/preprocessor_config.json b/checkpoint-3000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..98a41e66e16f3225a15cb2b51c963fe2213aa273
--- /dev/null
+++ b/checkpoint-3000/preprocessor_config.json
@@ -0,0 +1,19 @@
+{
+  "do_normalize": false,
+  "feature_extractor_type": "SpeechT5FeatureExtractor",
+  "feature_size": 1,
+  "fmax": 7600,
+  "fmin": 80,
+  "frame_signal_scale": 1.0,
+  "hop_length": 16,
+  "mel_floor": 1e-10,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "SpeechT5Processor",
+  "reduction_factor": 2,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "win_function": "hann_window",
+  "win_length": 64
+}
diff --git a/checkpoint-3000/rng_state.pth b/checkpoint-3000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..682fd4922c241432caa2166b49489da93d6f5b63
--- /dev/null
+++ b/checkpoint-3000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28e16300e84ad755819fc9d8ce7454fb75d39320dda51990693e5315c30d74b2
+size 14244
diff --git a/checkpoint-3000/scheduler.pt b/checkpoint-3000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..00802b7d7ba610674c2662a6888f78aa35c14408
--- /dev/null
+++ b/checkpoint-3000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff56efc76c16a3b9a712527179ae61c8d6dfccc7e3a53f8c421d6329adacfbb
+size 1064
diff --git a/checkpoint-3000/special_tokens_map.json b/checkpoint-3000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..4ee24ec69861cfc94abbe2c8c934aa0744aa623c
--- /dev/null
+++ b/checkpoint-3000/special_tokens_map.json
@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-3000/spm_char.model b/checkpoint-3000/spm_char.model
new file mode 100644
index 0000000000000000000000000000000000000000..8fb73691942626fa75df80b61aab0e9b9340d8e2
--- /dev/null
+++ b/checkpoint-3000/spm_char.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
+size 238473
diff --git a/checkpoint-3000/tokenizer_config.json b/checkpoint-3000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e8051ebd375d3357ac7b85aa5ba2982c351b423b
--- /dev/null
+++ b/checkpoint-3000/tokenizer_config.json
@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<ctc_blank>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 600,
+  "normalize": false,
+  "pad_token": "<pad>",
+  "processor_class": "SpeechT5Processor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "SpeechT5Tokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-3000/trainer_state.json b/checkpoint-3000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..1643dcd86cb69a7e8aef2a0526e2463680a28be1
--- /dev/null
+++ b/checkpoint-3000/trainer_state.json
@@ -0,0 +1,897 @@
+{
+  "best_metric": 0.44469836354255676,
+  "best_model_checkpoint": "speecht5_finetuned_voxpopuli_pl/checkpoint-3000",
+  "epoch": 15.075376884422111,
+  "eval_steps": 1000,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12562814070351758,
+      "grad_norm": 34.14754104614258,
+      "learning_rate": 4.6000000000000004e-07,
+      "loss": 6.2754,
+      "step": 25
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 25.906333923339844,
+      "learning_rate": 9.400000000000001e-07,
+      "loss": 6.1497,
+      "step": 50
+    },
+    {
+      "epoch": 0.3768844221105528,
+      "grad_norm": 29.097463607788086,
+      "learning_rate": 1.44e-06,
+      "loss": 6.0335,
+      "step": 75
+    },
+    {
+      "epoch": 0.5025125628140703,
+      "grad_norm": 18.543378829956055,
+      "learning_rate": 1.94e-06,
+      "loss": 5.8815,
+      "step": 100
+    },
+    {
+      "epoch": 0.628140703517588,
+      "grad_norm": 24.147188186645508,
+      "learning_rate": 2.4400000000000004e-06,
+      "loss": 5.5659,
+      "step": 125
+    },
+    {
+      "epoch": 0.7537688442211056,
+      "grad_norm": 15.634539604187012,
+      "learning_rate": 2.9400000000000002e-06,
+      "loss": 5.3573,
+      "step": 150
+    },
+    {
+      "epoch": 0.8793969849246231,
+      "grad_norm": 14.31460189819336,
+      "learning_rate": 3.44e-06,
+      "loss": 5.2616,
+      "step": 175
+    },
+    {
+      "epoch": 1.0050251256281406,
+      "grad_norm": 19.75978660583496,
+      "learning_rate": 3.94e-06,
+      "loss": 5.1787,
+      "step": 200
+    },
+    {
+      "epoch": 1.1306532663316582,
+      "grad_norm": 12.639854431152344,
+      "learning_rate": 4.440000000000001e-06,
+      "loss": 5.1214,
+      "step": 225
+    },
+    {
+      "epoch": 1.2562814070351758,
+      "grad_norm": 17.792396545410156,
+      "learning_rate": 4.94e-06,
+      "loss": 5.0703,
+      "step": 250
+    },
+    {
+      "epoch": 1.3819095477386933,
+      "grad_norm": 22.859201431274414,
+      "learning_rate": 5.4400000000000004e-06,
+      "loss": 4.9714,
+      "step": 275
+    },
+    {
+      "epoch": 1.507537688442211,
+      "grad_norm": 16.62458610534668,
+      "learning_rate": 5.94e-06,
+      "loss": 4.8681,
+      "step": 300
+    },
+    {
+      "epoch": 1.6331658291457285,
+      "grad_norm": 17.881174087524414,
+      "learning_rate": 6.440000000000001e-06,
+      "loss": 4.8252,
+      "step": 325
+    },
+    {
+      "epoch": 1.758793969849246,
+      "grad_norm": 14.765595436096191,
+      "learning_rate": 6.9400000000000005e-06,
+      "loss": 4.5588,
+      "step": 350
+    },
+    {
+      "epoch": 1.8844221105527639,
+      "grad_norm": 13.808978080749512,
+      "learning_rate": 7.440000000000001e-06,
+      "loss": 4.5211,
+      "step": 375
+    },
+    {
+      "epoch": 2.0100502512562812,
+      "grad_norm": 10.674385070800781,
+      "learning_rate": 7.94e-06,
+      "loss": 4.4888,
+      "step": 400
+    },
+    {
+      "epoch": 2.135678391959799,
+      "grad_norm": 15.555588722229004,
+      "learning_rate": 8.44e-06,
+      "loss": 4.4513,
+      "step": 425
+    },
+    {
+      "epoch": 2.2613065326633164,
+      "grad_norm": 13.092530250549316,
+      "learning_rate": 8.94e-06,
+      "loss": 4.3646,
+      "step": 450
+    },
+    {
+      "epoch": 2.3869346733668344,
+      "grad_norm": 12.971352577209473,
+      "learning_rate": 9.440000000000001e-06,
+      "loss": 4.3459,
+      "step": 475
+    },
+    {
+      "epoch": 2.5125628140703515,
+      "grad_norm": 10.348517417907715,
+      "learning_rate": 9.940000000000001e-06,
+      "loss": 4.2915,
+      "step": 500
+    },
+    {
+      "epoch": 2.6381909547738696,
+      "grad_norm": 13.625853538513184,
+      "learning_rate": 9.937142857142858e-06,
+      "loss": 4.3095,
+      "step": 525
+    },
+    {
+      "epoch": 2.7638190954773867,
+      "grad_norm": 11.426923751831055,
+      "learning_rate": 9.865714285714285e-06,
+      "loss": 4.1899,
+      "step": 550
+    },
+    {
+      "epoch": 2.8894472361809047,
+      "grad_norm": 11.516312599182129,
+      "learning_rate": 9.794285714285714e-06,
+      "loss": 4.2233,
+      "step": 575
+    },
+    {
+      "epoch": 3.0150753768844223,
+      "grad_norm": 16.141698837280273,
+      "learning_rate": 9.722857142857143e-06,
+      "loss": 4.1831,
+      "step": 600
+    },
+    {
+      "epoch": 3.14070351758794,
+      "grad_norm": 14.935202598571777,
+      "learning_rate": 9.651428571428572e-06,
+      "loss": 4.1739,
+      "step": 625
+    },
+    {
+      "epoch": 3.2663316582914574,
+      "grad_norm": 10.119762420654297,
+      "learning_rate": 9.58e-06,
+      "loss": 4.1649,
+      "step": 650
+    },
+    {
+      "epoch": 3.391959798994975,
+      "grad_norm": 16.50948143005371,
+      "learning_rate": 9.508571428571429e-06,
+      "loss": 4.1627,
+      "step": 675
+    },
+    {
+      "epoch": 3.5175879396984926,
+      "grad_norm": 10.08300495147705,
+      "learning_rate": 9.437142857142858e-06,
+      "loss": 4.1915,
+      "step": 700
+    },
+    {
+      "epoch": 3.64321608040201,
+      "grad_norm": 9.375288963317871,
+      "learning_rate": 9.365714285714287e-06,
+      "loss": 4.1279,
+      "step": 725
+    },
+    {
+      "epoch": 3.7688442211055277,
+      "grad_norm": 13.562234878540039,
+      "learning_rate": 9.294285714285714e-06,
+      "loss": 4.1083,
+      "step": 750
+    },
+    {
+      "epoch": 3.8944723618090453,
+      "grad_norm": 15.115653991699219,
+      "learning_rate": 9.222857142857143e-06,
+      "loss": 4.1236,
+      "step": 775
+    },
+    {
+      "epoch": 4.0201005025125625,
+      "grad_norm": 9.049237251281738,
+      "learning_rate": 9.151428571428572e-06,
+      "loss": 4.0964,
+      "step": 800
+    },
+    {
+      "epoch": 4.1457286432160805,
+      "grad_norm": 9.250771522521973,
+      "learning_rate": 9.080000000000001e-06,
+      "loss": 4.0669,
+      "step": 825
+    },
+    {
+      "epoch": 4.271356783919598,
+      "grad_norm": 12.07302474975586,
+      "learning_rate": 9.00857142857143e-06,
+      "loss": 4.0587,
+      "step": 850
+    },
+    {
+      "epoch": 4.396984924623116,
+      "grad_norm": 9.538933753967285,
+      "learning_rate": 8.937142857142857e-06,
+      "loss": 4.0837,
+      "step": 875
+    },
+    {
+      "epoch": 4.522613065326633,
+      "grad_norm": 14.347626686096191,
+      "learning_rate": 8.865714285714287e-06,
+      "loss": 4.0086,
+      "step": 900
+    },
+    {
+      "epoch": 4.648241206030151,
+      "grad_norm": 10.831369400024414,
+      "learning_rate": 8.794285714285716e-06,
+      "loss": 4.0563,
+      "step": 925
+    },
+    {
+      "epoch": 4.773869346733669,
+      "grad_norm": 9.891343116760254,
+      "learning_rate": 8.722857142857145e-06,
+      "loss": 4.0057,
+      "step": 950
+    },
+    {
+      "epoch": 4.899497487437186,
+      "grad_norm": 9.572471618652344,
+      "learning_rate": 8.651428571428572e-06,
+      "loss": 4.0557,
+      "step": 975
+    },
+    {
+      "epoch": 5.025125628140704,
+      "grad_norm": 9.745298385620117,
+      "learning_rate": 8.580000000000001e-06,
+      "loss": 3.9902,
+      "step": 1000
+    },
+    {
+      "epoch": 5.025125628140704,
+      "eval_loss": 0.46117448806762695,
+      "eval_runtime": 75.4681,
+      "eval_samples_per_second": 9.381,
+      "eval_steps_per_second": 4.691,
+      "step": 1000
+    },
+    {
+      "epoch": 5.150753768844221,
+      "grad_norm": 10.219923973083496,
+      "learning_rate": 8.50857142857143e-06,
+      "loss": 3.9991,
+      "step": 1025
+    },
+    {
+      "epoch": 5.276381909547739,
+      "grad_norm": 9.258833885192871,
+      "learning_rate": 8.437142857142859e-06,
+      "loss": 4.0032,
+      "step": 1050
+    },
+    {
+      "epoch": 5.402010050251256,
+      "grad_norm": 12.21104907989502,
+      "learning_rate": 8.365714285714286e-06,
+      "loss": 4.0337,
+      "step": 1075
+    },
+    {
+      "epoch": 5.527638190954773,
+      "grad_norm": 10.777599334716797,
+      "learning_rate": 8.294285714285715e-06,
+      "loss": 4.0036,
+      "step": 1100
+    },
+    {
+      "epoch": 5.653266331658291,
+      "grad_norm": 10.322349548339844,
+      "learning_rate": 8.222857142857144e-06,
+      "loss": 3.9811,
+      "step": 1125
+    },
+    {
+      "epoch": 5.778894472361809,
+      "grad_norm": 9.940053939819336,
+      "learning_rate": 8.151428571428572e-06,
+      "loss": 4.0264,
+      "step": 1150
+    },
+    {
+      "epoch": 5.9045226130653266,
+      "grad_norm": 12.996850967407227,
+      "learning_rate": 8.08e-06,
+      "loss": 3.9783,
+      "step": 1175
+    },
+    {
+      "epoch": 6.030150753768845,
+      "grad_norm": 10.784270286560059,
+      "learning_rate": 8.00857142857143e-06,
+      "loss": 3.936,
+      "step": 1200
+    },
+    {
+      "epoch": 6.155778894472362,
+      "grad_norm": 10.86549186706543,
+      "learning_rate": 7.937142857142857e-06,
+      "loss": 3.9803,
+      "step": 1225
+    },
+    {
+      "epoch": 6.28140703517588,
+      "grad_norm": 10.926647186279297,
+      "learning_rate": 7.865714285714286e-06,
+      "loss": 3.9587,
+      "step": 1250
+    },
+    {
+      "epoch": 6.407035175879397,
+      "grad_norm": 12.103693008422852,
+      "learning_rate": 7.794285714285715e-06,
+      "loss": 3.9441,
+      "step": 1275
+    },
+    {
+      "epoch": 6.532663316582915,
+      "grad_norm": 14.731566429138184,
+      "learning_rate": 7.722857142857142e-06,
+      "loss": 3.9541,
+      "step": 1300
+    },
+    {
+      "epoch": 6.658291457286432,
+      "grad_norm": 13.810087203979492,
+      "learning_rate": 7.651428571428571e-06,
+      "loss": 3.962,
+      "step": 1325
+    },
+    {
+      "epoch": 6.78391959798995,
+      "grad_norm": 10.733597755432129,
+      "learning_rate": 7.58e-06,
+      "loss": 3.9696,
+      "step": 1350
+    },
+    {
+      "epoch": 6.909547738693467,
+      "grad_norm": 12.271906852722168,
+      "learning_rate": 7.508571428571429e-06,
+      "loss": 3.9319,
+      "step": 1375
+    },
+    {
+      "epoch": 7.035175879396985,
+      "grad_norm": 17.454214096069336,
+      "learning_rate": 7.4371428571428575e-06,
+      "loss": 3.9096,
+      "step": 1400
+    },
+    {
+      "epoch": 7.160804020100502,
+      "grad_norm": 9.891731262207031,
+      "learning_rate": 7.365714285714286e-06,
+      "loss": 3.963,
+      "step": 1425
+    },
+    {
+      "epoch": 7.28643216080402,
+      "grad_norm": 10.400883674621582,
+      "learning_rate": 7.294285714285715e-06,
+      "loss": 3.9529,
+      "step": 1450
+    },
+    {
+      "epoch": 7.4120603015075375,
+      "grad_norm": 8.886434555053711,
+      "learning_rate": 7.222857142857144e-06,
+      "loss": 3.9048,
+      "step": 1475
+    },
+    {
+      "epoch": 7.5376884422110555,
+      "grad_norm": 13.72711181640625,
+      "learning_rate": 7.151428571428573e-06,
+      "loss": 3.9097,
+      "step": 1500
+    },
+    {
+      "epoch": 7.663316582914573,
+      "grad_norm": 10.161803245544434,
+      "learning_rate": 7.08e-06,
+      "loss": 3.9029,
+      "step": 1525
+    },
+    {
+      "epoch": 7.788944723618091,
+      "grad_norm": 9.717086791992188,
+      "learning_rate": 7.008571428571429e-06,
+      "loss": 3.9028,
+      "step": 1550
+    },
+    {
+      "epoch": 7.914572864321608,
+      "grad_norm": 9.483698844909668,
+      "learning_rate": 6.937142857142858e-06,
+      "loss": 3.9157,
+      "step": 1575
+    },
+    {
+      "epoch": 8.040201005025125,
+      "grad_norm": 8.951908111572266,
+      "learning_rate": 6.865714285714287e-06,
+      "loss": 3.9106,
+      "step": 1600
+    },
+    {
+      "epoch": 8.165829145728644,
+      "grad_norm": 8.099654197692871,
+      "learning_rate": 6.794285714285714e-06,
+      "loss": 3.9062,
+      "step": 1625
+    },
+    {
+      "epoch": 8.291457286432161,
+      "grad_norm": 10.005452156066895,
+      "learning_rate": 6.722857142857143e-06,
+      "loss": 3.9139,
+      "step": 1650
+    },
+    {
+      "epoch": 8.417085427135678,
+      "grad_norm": 7.832030296325684,
+      "learning_rate": 6.651428571428572e-06,
+      "loss": 3.8731,
+      "step": 1675
+    },
+    {
+      "epoch": 8.542713567839195,
+      "grad_norm": 9.519272804260254,
+      "learning_rate": 6.5800000000000005e-06,
+      "loss": 3.9234,
+      "step": 1700
+    },
+    {
+      "epoch": 8.668341708542714,
+      "grad_norm": 7.6004252433776855,
+      "learning_rate": 6.5085714285714295e-06,
+      "loss": 3.8889,
+      "step": 1725
+    },
+    {
+      "epoch": 8.793969849246231,
+      "grad_norm": 8.43916130065918,
+      "learning_rate": 6.437142857142858e-06,
+      "loss": 3.8813,
+      "step": 1750
+    },
+    {
+      "epoch": 8.919597989949748,
+      "grad_norm": 9.573629379272461,
+      "learning_rate": 6.365714285714286e-06,
+      "loss": 3.9234,
+      "step": 1775
+    },
+    {
+      "epoch": 9.045226130653266,
+      "grad_norm": 11.034466743469238,
+      "learning_rate": 6.294285714285715e-06,
+      "loss": 3.9227,
+      "step": 1800
+    },
+    {
+      "epoch": 9.170854271356784,
+      "grad_norm": 9.65125560760498,
+      "learning_rate": 6.222857142857144e-06,
+      "loss": 3.8806,
+      "step": 1825
+    },
+    {
+      "epoch": 9.296482412060302,
+      "grad_norm": 8.907113075256348,
+      "learning_rate": 6.151428571428571e-06,
+      "loss": 3.8878,
+      "step": 1850
+    },
+    {
+      "epoch": 9.422110552763819,
+      "grad_norm": 9.000490188598633,
+      "learning_rate": 6.08e-06,
+      "loss": 3.858,
+      "step": 1875
+    },
+    {
+      "epoch": 9.547738693467338,
+      "grad_norm": 10.825636863708496,
+      "learning_rate": 6.008571428571429e-06,
+      "loss": 3.8546,
+      "step": 1900
+    },
+    {
+      "epoch": 9.673366834170855,
+      "grad_norm": 8.722935676574707,
+      "learning_rate": 5.937142857142858e-06,
+      "loss": 3.871,
+      "step": 1925
+    },
+    {
+      "epoch": 9.798994974874372,
+      "grad_norm": 9.243980407714844,
+      "learning_rate": 5.865714285714286e-06,
+      "loss": 3.8486,
+      "step": 1950
+    },
+    {
+      "epoch": 9.924623115577889,
+      "grad_norm": 10.595390319824219,
+      "learning_rate": 5.794285714285715e-06,
+      "loss": 3.8973,
+      "step": 1975
+    },
+    {
+      "epoch": 10.050251256281408,
+      "grad_norm": 11.8334321975708,
+      "learning_rate": 5.722857142857144e-06,
+      "loss": 3.8124,
+      "step": 2000
+    },
+    {
+      "epoch": 10.050251256281408,
+      "eval_loss": 0.44917792081832886,
+      "eval_runtime": 76.9989,
+      "eval_samples_per_second": 9.195,
+      "eval_steps_per_second": 4.597,
+      "step": 2000
+    },
+    {
+      "epoch": 10.175879396984925,
+      "grad_norm": 12.580653190612793,
+      "learning_rate": 5.651428571428572e-06,
+      "loss": 3.8754,
+      "step": 2025
+    },
+    {
+      "epoch": 10.301507537688442,
+      "grad_norm": 9.411772727966309,
+      "learning_rate": 5.582857142857143e-06,
+      "loss": 3.839,
+      "step": 2050
+    },
+    {
+      "epoch": 10.42713567839196,
+      "grad_norm": 8.65829849243164,
+      "learning_rate": 5.511428571428572e-06,
+      "loss": 3.8123,
+      "step": 2075
+    },
+    {
+      "epoch": 10.552763819095478,
+      "grad_norm": 9.79350757598877,
+      "learning_rate": 5.4400000000000004e-06,
+      "loss": 3.8609,
+      "step": 2100
+    },
+    {
+      "epoch": 10.678391959798995,
+      "grad_norm": 9.445945739746094,
+      "learning_rate": 5.368571428571429e-06,
+      "loss": 3.8359,
+      "step": 2125
+    },
+    {
+      "epoch": 10.804020100502512,
+      "grad_norm": 11.811120986938477,
+      "learning_rate": 5.297142857142858e-06,
+      "loss": 3.8632,
+      "step": 2150
+    },
+    {
+      "epoch": 10.92964824120603,
+      "grad_norm": 10.508607864379883,
+      "learning_rate": 5.225714285714286e-06,
+      "loss": 3.8324,
+      "step": 2175
+    },
+    {
+      "epoch": 11.055276381909549,
+      "grad_norm": 8.808614730834961,
+      "learning_rate": 5.154285714285715e-06,
+      "loss": 3.8314,
+      "step": 2200
+    },
+    {
+      "epoch": 11.180904522613066,
+      "grad_norm": 11.709993362426758,
+      "learning_rate": 5.082857142857144e-06,
+      "loss": 3.8904,
+      "step": 2225
+    },
+    {
+      "epoch": 11.306532663316583,
+      "grad_norm": 8.451616287231445,
+      "learning_rate": 5.011428571428571e-06,
+      "loss": 3.8471,
+      "step": 2250
+    },
+    {
+      "epoch": 11.4321608040201,
+      "grad_norm": 10.084294319152832,
+      "learning_rate": 4.94e-06,
+      "loss": 3.8881,
+      "step": 2275
+    },
+    {
+      "epoch": 11.557788944723619,
+      "grad_norm": 17.51856803894043,
+      "learning_rate": 4.868571428571429e-06,
+      "loss": 3.8931,
+      "step": 2300
+    },
+    {
+      "epoch": 11.683417085427136,
+      "grad_norm": 11.671639442443848,
+      "learning_rate": 4.797142857142857e-06,
+      "loss": 3.8578,
+      "step": 2325
+    },
+    {
+      "epoch": 11.809045226130653,
+      "grad_norm": 8.713754653930664,
+      "learning_rate": 4.725714285714286e-06,
+      "loss": 3.832,
+      "step": 2350
+    },
+    {
+      "epoch": 11.93467336683417,
+      "grad_norm": 11.429880142211914,
+      "learning_rate": 4.6542857142857145e-06,
+      "loss": 3.8556,
+      "step": 2375
+    },
+    {
+      "epoch": 12.06030150753769,
+      "grad_norm": 9.178875923156738,
+      "learning_rate": 4.5828571428571435e-06,
+      "loss": 3.8361,
+      "step": 2400
+    },
+    {
+      "epoch": 12.185929648241206,
+      "grad_norm": 7.655440330505371,
+      "learning_rate": 4.511428571428572e-06,
+      "loss": 3.8337,
+      "step": 2425
+    },
+    {
+      "epoch": 12.311557788944723,
+      "grad_norm": 10.44965648651123,
+      "learning_rate": 4.440000000000001e-06,
+      "loss": 3.877,
+      "step": 2450
+    },
+    {
+      "epoch": 12.43718592964824,
+      "grad_norm": 9.04977035522461,
+      "learning_rate": 4.368571428571429e-06,
+      "loss": 3.8504,
+      "step": 2475
+    },
+    {
+      "epoch": 12.56281407035176,
+      "grad_norm": 8.15368366241455,
+      "learning_rate": 4.297142857142858e-06,
+      "loss": 3.8297,
+      "step": 2500
+    },
+    {
+      "epoch": 12.688442211055277,
+      "grad_norm": 9.811213493347168,
+      "learning_rate": 4.225714285714286e-06,
+      "loss": 3.8289,
+      "step": 2525
+    },
+    {
+      "epoch": 12.814070351758794,
+      "grad_norm": 8.397767066955566,
+      "learning_rate": 4.154285714285714e-06,
+      "loss": 3.8352,
+      "step": 2550
+    },
+    {
+      "epoch": 12.93969849246231,
+      "grad_norm": 10.471597671508789,
+      "learning_rate": 4.082857142857143e-06,
+      "loss": 3.8438,
+      "step": 2575
+    },
+    {
+      "epoch": 13.06532663316583,
+      "grad_norm": 8.042658805847168,
+      "learning_rate": 4.011428571428571e-06,
+      "loss": 3.8308,
+      "step": 2600
+    },
+    {
+      "epoch": 13.190954773869347,
+      "grad_norm": 9.240007400512695,
+      "learning_rate": 3.94e-06,
+      "loss": 3.811,
+      "step": 2625
+    },
+    {
+      "epoch": 13.316582914572864,
+      "grad_norm": 8.514374732971191,
+      "learning_rate": 3.8685714285714286e-06,
+      "loss": 3.8253,
+      "step": 2650
+    },
+    {
+      "epoch": 13.442211055276381,
+      "grad_norm": 8.689332008361816,
+      "learning_rate": 3.7971428571428576e-06,
+      "loss": 3.8387,
+      "step": 2675
+    },
+    {
+      "epoch": 13.5678391959799,
+      "grad_norm": 11.250374794006348,
+      "learning_rate": 3.7257142857142857e-06,
+      "loss": 3.8216,
+      "step": 2700
+    },
+    {
+      "epoch": 13.693467336683417,
+      "grad_norm": 8.129416465759277,
+      "learning_rate": 3.6542857142857148e-06,
+      "loss": 3.8273,
+      "step": 2725
+    },
+    {
+      "epoch": 13.819095477386934,
+      "grad_norm": 9.398397445678711,
+      "learning_rate": 3.582857142857143e-06,
+      "loss": 3.8116,
+      "step": 2750
+    },
+    {
+      "epoch": 13.944723618090451,
+      "grad_norm": 9.966887474060059,
+      "learning_rate": 3.511428571428572e-06,
+      "loss": 3.8401,
+      "step": 2775
+    },
+    {
+      "epoch": 14.07035175879397,
+      "grad_norm": 7.829891204833984,
+      "learning_rate": 3.44e-06,
+      "loss": 3.7607,
+      "step": 2800
+    },
+    {
+      "epoch": 14.195979899497488,
+      "grad_norm": 10.33727741241455,
+      "learning_rate": 3.3685714285714287e-06,
+      "loss": 3.8406,
+      "step": 2825
+    },
+    {
+      "epoch": 14.321608040201005,
+      "grad_norm": 8.579668998718262,
+      "learning_rate": 3.2971428571428577e-06,
+      "loss": 3.7893,
+      "step": 2850
+    },
+    {
+      "epoch": 14.447236180904522,
+      "grad_norm": 9.909623146057129,
+      "learning_rate": 3.225714285714286e-06,
+      "loss": 3.8661,
+      "step": 2875
+    },
+    {
+      "epoch": 14.57286432160804,
+      "grad_norm": 9.630623817443848,
+      "learning_rate": 3.154285714285715e-06,
+      "loss": 3.8248,
+      "step": 2900
+    },
+    {
+      "epoch": 14.698492462311558,
+      "grad_norm": 13.711705207824707,
+      "learning_rate": 3.082857142857143e-06,
+      "loss": 3.8268,
+      "step": 2925
+    },
+    {
+      "epoch": 14.824120603015075,
+      "grad_norm": 8.66063117980957,
+      "learning_rate": 3.0114285714285716e-06,
+      "loss": 3.8154,
+      "step": 2950
+    },
+    {
+      "epoch": 14.949748743718594,
+      "grad_norm": 10.465475082397461,
+      "learning_rate": 2.9400000000000002e-06,
+      "loss": 3.826,
+      "step": 2975
+    },
+    {
+      "epoch": 15.075376884422111,
+      "grad_norm": 9.025050163269043,
+      "learning_rate": 2.868571428571429e-06,
+      "loss": 3.8132,
+      "step": 3000
+    },
+    {
+      "epoch": 15.075376884422111,
+      "eval_loss": 0.44469836354255676,
+      "eval_runtime": 78.3312,
+      "eval_samples_per_second": 9.039,
+      "eval_steps_per_second": 4.519,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 21,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3502296824093e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-3000/training_args.bin b/checkpoint-3000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6ccf0404925f6a8a3bda1ade1cb95630a3b1750a
--- /dev/null
+++ b/checkpoint-3000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6ae756af4eb40168228ea5b672dedd9146f11deae4f8d64668e0b2d5a69781
+size 5432
diff --git a/checkpoint-4000/added_tokens.json b/checkpoint-4000/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..cd5b477a9075c49d99de65622db37bb06a251985
--- /dev/null
+++ b/checkpoint-4000/added_tokens.json
@@ -0,0 +1,4 @@
+{
+  "<ctc_blank>": 80,
+  "<mask>": 79
+}
diff --git a/checkpoint-4000/config.json b/checkpoint-4000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..778ad24a356630d39cc083e2d1df5699c25c0278
--- /dev/null
+++ b/checkpoint-4000/config.json
@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "microsoft/speecht5_tts",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SpeechT5ForTextToSpeech"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.1,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.1,
+  "encoder_layers": 12,
+  "encoder_max_relative_position": 160,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "guided_attention_loss_num_heads": 2,
+  "guided_attention_loss_scale": 10.0,
+  "guided_attention_loss_sigma": 0.4,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": null,
+  "max_speech_positions": 1876,
+  "max_text_positions": 600,
+  "model_type": "speecht5",
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_mel_bins": 80,
+  "pad_token_id": 1,
+  "positional_dropout": 0.1,
+  "reduction_factor": 2,
+  "scale_embedding": false,
+  "speaker_embedding_dim": 512,
+  "speech_decoder_postnet_dropout": 0.5,
+  "speech_decoder_postnet_kernel": 5,
+  "speech_decoder_postnet_layers": 5,
+  "speech_decoder_postnet_units": 256,
+  "speech_decoder_prenet_dropout": 0.5,
+  "speech_decoder_prenet_layers": 2,
+  "speech_decoder_prenet_units": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_guided_attention_loss": true,
+  "vocab_size": 81
+}
diff --git a/checkpoint-4000/generation_config.json b/checkpoint-4000/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5c3f497ae3f531fba6f7d3d8ed048ed02f110db1
--- /dev/null
+++ b/checkpoint-4000/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 1876,
+  "pad_token_id": 1,
+  "transformers_version": "4.46.1"
+}
diff --git a/checkpoint-4000/model.safetensors b/checkpoint-4000/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1e5aa021d3a2df7f71ad69c63d8dcd44b5cd212b
--- /dev/null
+++ b/checkpoint-4000/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef602e8e24bc81f46de9f25767181905eb11eef70a202f911f339f87f352347
+size 577789320
diff --git a/checkpoint-4000/optimizer.pt b/checkpoint-4000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..85a923abf9ad1a74db255883a6c8bd0ff5606696
--- /dev/null
+++ b/checkpoint-4000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8420507944acab9b5096619d2ae70286620e694ab3f8a5679789b8e6eca4260
+size 1155772233
diff --git a/checkpoint-4000/preprocessor_config.json b/checkpoint-4000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..98a41e66e16f3225a15cb2b51c963fe2213aa273
--- /dev/null
+++ b/checkpoint-4000/preprocessor_config.json
@@ -0,0 +1,19 @@
+{
+  "do_normalize": false,
+  "feature_extractor_type": "SpeechT5FeatureExtractor",
+  "feature_size": 1,
+  "fmax": 7600,
+  "fmin": 80,
+  "frame_signal_scale": 1.0,
+  "hop_length": 16,
+  "mel_floor": 1e-10,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "SpeechT5Processor",
+  "reduction_factor": 2,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "win_function": "hann_window",
+  "win_length": 64
+}
diff --git a/checkpoint-4000/rng_state.pth b/checkpoint-4000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d9bdb8fb7cf5dc0186d9fdf0ae71f186afaa4fd5
--- /dev/null
+++ b/checkpoint-4000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f46389eb0872e6838f448d5803d25f4f567ce04f0cad9805ddd1e11b37f2317
+size 14244
diff --git a/checkpoint-4000/scheduler.pt b/checkpoint-4000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bbf6940bd360ad866b84117412902669203f8f21
--- /dev/null
+++ b/checkpoint-4000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7efbf80617c96c78286826ce59d9a12c86da62d7631874b3d6364a8e993ada60
+size 1064
diff --git a/checkpoint-4000/special_tokens_map.json b/checkpoint-4000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..4ee24ec69861cfc94abbe2c8c934aa0744aa623c
--- /dev/null
+++ b/checkpoint-4000/special_tokens_map.json
@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-4000/spm_char.model b/checkpoint-4000/spm_char.model
new file mode 100644
index 0000000000000000000000000000000000000000..8fb73691942626fa75df80b61aab0e9b9340d8e2
--- /dev/null
+++ b/checkpoint-4000/spm_char.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
+size 238473
diff --git a/checkpoint-4000/tokenizer_config.json b/checkpoint-4000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e8051ebd375d3357ac7b85aa5ba2982c351b423b
--- /dev/null
+++ b/checkpoint-4000/tokenizer_config.json
@@ -0,0 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<ctc_blank>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 600,
+  "normalize": false,
+  "pad_token": "<pad>",
+  "processor_class": "SpeechT5Processor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "SpeechT5Tokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-4000/trainer_state.json b/checkpoint-4000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..5f16a519a156dc63e02eda612c86109ecd5a019a
--- /dev/null
+++ b/checkpoint-4000/trainer_state.json
@@ -0,0 +1,1185 @@
+{
+  "best_metric": 0.4429960548877716,
+  "best_model_checkpoint": "speecht5_finetuned_voxpopuli_pl/checkpoint-4000",
+  "epoch": 20.100502512562816,
+  "eval_steps": 1000,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12562814070351758,
+      "grad_norm": 34.14754104614258,
+      "learning_rate": 4.6000000000000004e-07,
+      "loss": 6.2754,
+      "step": 25
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 25.906333923339844,
+      "learning_rate": 9.400000000000001e-07,
+      "loss": 6.1497,
+      "step": 50
+    },
+    {
+      "epoch": 0.3768844221105528,
+      "grad_norm": 29.097463607788086,
+      "learning_rate": 1.44e-06,
+      "loss": 6.0335,
+      "step": 75
+    },
+    {
+      "epoch": 0.5025125628140703,
+      "grad_norm": 18.543378829956055,
+      "learning_rate": 1.94e-06,
+      "loss": 5.8815,
+      "step": 100
+    },
+    {
+      "epoch": 0.628140703517588,
+      "grad_norm": 24.147188186645508,
+      "learning_rate": 2.4400000000000004e-06,
+      "loss": 5.5659,
+      "step": 125
+    },
+    {
+      "epoch": 0.7537688442211056,
+      "grad_norm": 15.634539604187012,
+      "learning_rate": 2.9400000000000002e-06,
+      "loss": 5.3573,
+      "step": 150
+    },
+    {
+      "epoch": 0.8793969849246231,
+      "grad_norm": 14.31460189819336,
+      "learning_rate": 3.44e-06,
+      "loss": 5.2616,
+      "step": 175
+    },
+    {
+      "epoch": 1.0050251256281406,
+      "grad_norm": 19.75978660583496,
+      "learning_rate": 3.94e-06,
+      "loss": 5.1787,
+      "step": 200
+    },
+    {
+      "epoch": 1.1306532663316582,
+      "grad_norm": 12.639854431152344,
+      "learning_rate": 4.440000000000001e-06,
+      "loss": 5.1214,
+      "step": 225
+    },
+    {
+      "epoch": 1.2562814070351758,
+      "grad_norm": 17.792396545410156,
+      "learning_rate": 4.94e-06,
+      "loss": 5.0703,
+      "step": 250
+    },
+    {
+      "epoch": 1.3819095477386933,
+      "grad_norm": 22.859201431274414,
+      "learning_rate": 5.4400000000000004e-06,
+      "loss": 4.9714,
+      "step": 275
+    },
+    {
+      "epoch": 1.507537688442211,
+      "grad_norm": 16.62458610534668,
+      "learning_rate": 5.94e-06,
+      "loss": 4.8681,
+      "step": 300
+    },
+    {
+      "epoch": 1.6331658291457285,
+      "grad_norm": 17.881174087524414,
+      "learning_rate": 6.440000000000001e-06,
+      "loss": 4.8252,
+      "step": 325
+    },
+    {
+      "epoch": 1.758793969849246,
+      "grad_norm": 14.765595436096191,
+      "learning_rate": 6.9400000000000005e-06,
+      "loss": 4.5588,
+      "step": 350
+    },
+    {
+      "epoch": 1.8844221105527639,
+      "grad_norm": 13.808978080749512,
+      "learning_rate": 7.440000000000001e-06,
+      "loss": 4.5211,
+      "step": 375
+    },
+    {
+      "epoch": 2.0100502512562812,
+      "grad_norm": 10.674385070800781,
+      "learning_rate": 7.94e-06,
+      "loss": 4.4888,
+      "step": 400
+    },
+    {
+      "epoch": 2.135678391959799,
+      "grad_norm": 15.555588722229004,
+      "learning_rate": 8.44e-06,
+      "loss": 4.4513,
+      "step": 425
+    },
+    {
+      "epoch": 2.2613065326633164,
+      "grad_norm": 13.092530250549316,
+      "learning_rate": 8.94e-06,
+      "loss": 4.3646,
+      "step": 450
+    },
+    {
+      "epoch": 2.3869346733668344,
+      "grad_norm": 12.971352577209473,
+      "learning_rate": 9.440000000000001e-06,
+      "loss": 4.3459,
+      "step": 475
+    },
+    {
+      "epoch": 2.5125628140703515,
+      "grad_norm": 10.348517417907715,
+      "learning_rate": 9.940000000000001e-06,
+      "loss": 4.2915,
+      "step": 500
+    },
+    {
+      "epoch": 2.6381909547738696,
+      "grad_norm": 13.625853538513184,
+      "learning_rate": 9.937142857142858e-06,
+      "loss": 4.3095,
+      "step": 525
+    },
+    {
+      "epoch": 2.7638190954773867,
+      "grad_norm": 11.426923751831055,
+      "learning_rate": 9.865714285714285e-06,
+      "loss": 4.1899,
+      "step": 550
+    },
+    {
+      "epoch": 2.8894472361809047,
+      "grad_norm": 11.516312599182129,
+      "learning_rate": 9.794285714285714e-06,
+      "loss": 4.2233,
+      "step": 575
+    },
+    {
+      "epoch": 3.0150753768844223,
+      "grad_norm": 16.141698837280273,
+      "learning_rate": 9.722857142857143e-06,
+      "loss": 4.1831,
+      "step": 600
+    },
+    {
+      "epoch": 3.14070351758794,
+      "grad_norm": 14.935202598571777,
+      "learning_rate": 9.651428571428572e-06,
+      "loss": 4.1739,
+      "step": 625
+    },
+    {
+      "epoch": 3.2663316582914574,
+      "grad_norm": 10.119762420654297,
+      "learning_rate": 9.58e-06,
+      "loss": 4.1649,
+      "step": 650
+    },
+    {
+      "epoch": 3.391959798994975,
+      "grad_norm": 16.50948143005371,
+      "learning_rate": 9.508571428571429e-06,
+      "loss": 4.1627,
+      "step": 675
+    },
+    {
+      "epoch": 3.5175879396984926,
+      "grad_norm": 10.08300495147705,
+      "learning_rate": 9.437142857142858e-06,
+      "loss": 4.1915,
+      "step": 700
+    },
+    {
+      "epoch": 3.64321608040201,
+      "grad_norm": 9.375288963317871,
+      "learning_rate": 9.365714285714287e-06,
+      "loss": 4.1279,
+      "step": 725
+    },
+    {
+      "epoch": 3.7688442211055277,
+      "grad_norm": 13.562234878540039,
+      "learning_rate": 9.294285714285714e-06,
+      "loss": 4.1083,
+      "step": 750
+    },
+    {
+      "epoch": 3.8944723618090453,
+      "grad_norm": 15.115653991699219,
+      "learning_rate": 9.222857142857143e-06,
+      "loss": 4.1236,
+      "step": 775
+    },
+    {
+      "epoch": 4.0201005025125625,
+      "grad_norm": 9.049237251281738,
+      "learning_rate": 9.151428571428572e-06,
+      "loss": 4.0964,
+      "step": 800
+    },
+    {
+      "epoch": 4.1457286432160805,
+      "grad_norm": 9.250771522521973,
+      "learning_rate": 9.080000000000001e-06,
+      "loss": 4.0669,
+      "step": 825
+    },
+    {
+      "epoch": 4.271356783919598,
+      "grad_norm": 12.07302474975586,
+      "learning_rate": 9.00857142857143e-06,
+      "loss": 4.0587,
+      "step": 850
+    },
+    {
+      "epoch": 4.396984924623116,
+      "grad_norm": 9.538933753967285,
+      "learning_rate": 8.937142857142857e-06,
+      "loss": 4.0837,
+      "step": 875
+    },
+    {
+      "epoch": 4.522613065326633,
+      "grad_norm": 14.347626686096191,
+      "learning_rate": 8.865714285714287e-06,
+      "loss": 4.0086,
+      "step": 900
+    },
+    {
+      "epoch": 4.648241206030151,
+      "grad_norm": 10.831369400024414,
+      "learning_rate": 8.794285714285716e-06,
+      "loss": 4.0563,
+      "step": 925
+    },
+    {
+      "epoch": 4.773869346733669,
+      "grad_norm": 9.891343116760254,
+      "learning_rate": 8.722857142857145e-06,
+      "loss": 4.0057,
+      "step": 950
+    },
+    {
+      "epoch": 4.899497487437186,
+      "grad_norm": 9.572471618652344,
+      "learning_rate": 8.651428571428572e-06,
+      "loss": 4.0557,
+      "step": 975
+    },
+    {
+      "epoch": 5.025125628140704,
+      "grad_norm": 9.745298385620117,
+      "learning_rate": 8.580000000000001e-06,
+      "loss": 3.9902,
+      "step": 1000
+    },
+    {
+      "epoch": 5.025125628140704,
+      "eval_loss": 0.46117448806762695,
+      "eval_runtime": 75.4681,
+      "eval_samples_per_second": 9.381,
+      "eval_steps_per_second": 4.691,
+      "step": 1000
+    },
+    {
+      "epoch": 5.150753768844221,
+      "grad_norm": 10.219923973083496,
+      "learning_rate": 8.50857142857143e-06,
+      "loss": 3.9991,
+      "step": 1025
+    },
+    {
+      "epoch": 5.276381909547739,
+      "grad_norm": 9.258833885192871,
+      "learning_rate": 8.437142857142859e-06,
+      "loss": 4.0032,
+      "step": 1050
+    },
+    {
+      "epoch": 5.402010050251256,
+      "grad_norm": 12.21104907989502,
+      "learning_rate": 8.365714285714286e-06,
+      "loss": 4.0337,
+      "step": 1075
+    },
+    {
+      "epoch": 5.527638190954773,
+      "grad_norm": 10.777599334716797,
+      "learning_rate": 8.294285714285715e-06,
+      "loss": 4.0036,
+      "step": 1100
+    },
+    {
+      "epoch": 5.653266331658291,
+      "grad_norm": 10.322349548339844,
+      "learning_rate": 8.222857142857144e-06,
+      "loss": 3.9811,
+      "step": 1125
+    },
+    {
+      "epoch": 5.778894472361809,
+      "grad_norm": 9.940053939819336,
+      "learning_rate": 8.151428571428572e-06,
+      "loss": 4.0264,
+      "step": 1150
+    },
+    {
+      "epoch": 5.9045226130653266,
+      "grad_norm": 12.996850967407227,
+      "learning_rate": 8.08e-06,
+      "loss": 3.9783,
+      "step": 1175
+    },
+    {
+      "epoch": 6.030150753768845,
+      "grad_norm": 10.784270286560059,
+      "learning_rate": 8.00857142857143e-06,
+      "loss": 3.936,
+      "step": 1200
+    },
+    {
+      "epoch": 6.155778894472362,
+      "grad_norm": 10.86549186706543,
+      "learning_rate": 7.937142857142857e-06,
+      "loss": 3.9803,
+      "step": 1225
+    },
+    {
+      "epoch": 6.28140703517588,
+      "grad_norm": 10.926647186279297,
+      "learning_rate": 7.865714285714286e-06,
+      "loss": 3.9587,
+      "step": 1250
+    },
+    {
+      "epoch": 6.407035175879397,
+      "grad_norm": 12.103693008422852,
+      "learning_rate": 7.794285714285715e-06,
+      "loss": 3.9441,
+      "step": 1275
+    },
+    {
+      "epoch": 6.532663316582915,
+      "grad_norm": 14.731566429138184,
+      "learning_rate": 7.722857142857142e-06,
+      "loss": 3.9541,
+      "step": 1300
+    },
+    {
+      "epoch": 6.658291457286432,
+      "grad_norm": 13.810087203979492,
+      "learning_rate": 7.651428571428571e-06,
+      "loss": 3.962,
+      "step": 1325
+    },
+    {
+      "epoch": 6.78391959798995,
+      "grad_norm": 10.733597755432129,
+      "learning_rate": 7.58e-06,
+      "loss": 3.9696,
+      "step": 1350
+    },
+    {
+      "epoch": 6.909547738693467,
+      "grad_norm": 12.271906852722168,
+      "learning_rate": 7.508571428571429e-06,
+      "loss": 3.9319,
+      "step": 1375
+    },
+    {
+      "epoch": 7.035175879396985,
+      "grad_norm": 17.454214096069336,
+      "learning_rate": 7.4371428571428575e-06,
+      "loss": 3.9096,
+      "step": 1400
+    },
+    {
+      "epoch": 7.160804020100502,
+      "grad_norm": 9.891731262207031,
+      "learning_rate": 7.365714285714286e-06,
+      "loss": 3.963,
+      "step": 1425
+    },
+    {
+      "epoch": 7.28643216080402,
+      "grad_norm": 10.400883674621582,
+      "learning_rate": 7.294285714285715e-06,
+      "loss": 3.9529,
+      "step": 1450
+    },
+    {
+      "epoch": 7.4120603015075375,
+      "grad_norm": 8.886434555053711,
+      "learning_rate": 7.222857142857144e-06,
+      "loss": 3.9048,
+      "step": 1475
+    },
+    {
+      "epoch": 7.5376884422110555,
+      "grad_norm": 13.72711181640625,
+      "learning_rate": 7.151428571428573e-06,
+      "loss": 3.9097,
+      "step": 1500
+    },
+    {
+      "epoch": 7.663316582914573,
+      "grad_norm": 10.161803245544434,
+      "learning_rate": 7.08e-06,
+      "loss": 3.9029,
+      "step": 1525
+    },
+    {
+      "epoch": 7.788944723618091,
+      "grad_norm": 9.717086791992188,
+      "learning_rate": 7.008571428571429e-06,
+      "loss": 3.9028,
+      "step": 1550
+    },
+    {
+      "epoch": 7.914572864321608,
+      "grad_norm": 9.483698844909668,
+      "learning_rate": 6.937142857142858e-06,
+      "loss": 3.9157,
+      "step": 1575
+    },
+    {
+      "epoch": 8.040201005025125,
+      "grad_norm": 8.951908111572266,
+      "learning_rate": 6.865714285714287e-06,
+      "loss": 3.9106,
+      "step": 1600
+    },
+    {
+      "epoch": 8.165829145728644,
+      "grad_norm": 8.099654197692871,
+      "learning_rate": 6.794285714285714e-06,
+      "loss": 3.9062,
+      "step": 1625
+    },
+    {
+      "epoch": 8.291457286432161,
+      "grad_norm": 10.005452156066895,
+      "learning_rate": 6.722857142857143e-06,
+      "loss": 3.9139,
+      "step": 1650
+    },
+    {
+      "epoch": 8.417085427135678,
+      "grad_norm": 7.832030296325684,
+      "learning_rate": 6.651428571428572e-06,
+      "loss": 3.8731,
+      "step": 1675
+    },
+    {
+      "epoch": 8.542713567839195,
+      "grad_norm": 9.519272804260254,
+      "learning_rate": 6.5800000000000005e-06,
+      "loss": 3.9234,
+      "step": 1700
+    },
+    {
+      "epoch": 8.668341708542714,
+      "grad_norm": 7.6004252433776855,
+      "learning_rate": 6.5085714285714295e-06,
+      "loss": 3.8889,
+      "step": 1725
+    },
+    {
+      "epoch": 8.793969849246231,
+      "grad_norm": 8.43916130065918,
+      "learning_rate": 6.437142857142858e-06,
+      "loss": 3.8813,
+      "step": 1750
+    },
+    {
+      "epoch": 8.919597989949748,
+      "grad_norm": 9.573629379272461,
+      "learning_rate": 6.365714285714286e-06,
+      "loss": 3.9234,
+      "step": 1775
+    },
+    {
+      "epoch": 9.045226130653266,
+      "grad_norm": 11.034466743469238,
+      "learning_rate": 6.294285714285715e-06,
+      "loss": 3.9227,
+      "step": 1800
+    },
+    {
+      "epoch": 9.170854271356784,
+      "grad_norm": 9.65125560760498,
+      "learning_rate": 6.222857142857144e-06,
+      "loss": 3.8806,
+      "step": 1825
+    },
+    {
+      "epoch": 9.296482412060302,
+      "grad_norm": 8.907113075256348,
+      "learning_rate": 6.151428571428571e-06,
+      "loss": 3.8878,
+      "step": 1850
+    },
+    {
+      "epoch": 9.422110552763819,
+      "grad_norm": 9.000490188598633,
+      "learning_rate": 6.08e-06,
+      "loss": 3.858,
+      "step": 1875
+    },
+    {
+      "epoch": 9.547738693467338,
+      "grad_norm": 10.825636863708496,
+      "learning_rate": 6.008571428571429e-06,
+      "loss": 3.8546,
+      "step": 1900
+    },
+    {
+      "epoch": 9.673366834170855,
+      "grad_norm": 8.722935676574707,
+      "learning_rate": 5.937142857142858e-06,
+      "loss": 3.871,
+      "step": 1925
+    },
+    {
+      "epoch": 9.798994974874372,
+      "grad_norm": 9.243980407714844,
+      "learning_rate": 5.865714285714286e-06,
+      "loss": 3.8486,
+      "step": 1950
+    },
+    {
+      "epoch": 9.924623115577889,
+      "grad_norm": 10.595390319824219,
+      "learning_rate": 5.794285714285715e-06,
+      "loss": 3.8973,
+      "step": 1975
+    },
+    {
+      "epoch": 10.050251256281408,
+      "grad_norm": 11.8334321975708,
+      "learning_rate": 5.722857142857144e-06,
+      "loss": 3.8124,
+      "step": 2000
+    },
+    {
+      "epoch": 10.050251256281408,
+      "eval_loss": 0.44917792081832886,
+      "eval_runtime": 76.9989,
+      "eval_samples_per_second": 9.195,
+      "eval_steps_per_second": 4.597,
+      "step": 2000
+    },
+    {
+      "epoch": 10.175879396984925,
+      "grad_norm": 12.580653190612793,
+      "learning_rate": 5.651428571428572e-06,
+      "loss": 3.8754,
+      "step": 2025
+    },
+    {
+      "epoch": 10.301507537688442,
+      "grad_norm": 9.411772727966309,
+      "learning_rate": 5.582857142857143e-06,
+      "loss": 3.839,
+      "step": 2050
+    },
+    {
+      "epoch": 10.42713567839196,
+      "grad_norm": 8.65829849243164,
+      "learning_rate": 5.511428571428572e-06,
+      "loss": 3.8123,
+      "step": 2075
+    },
+    {
+      "epoch": 10.552763819095478,
+      "grad_norm": 9.79350757598877,
+      "learning_rate": 5.4400000000000004e-06,
+      "loss": 3.8609,
+      "step": 2100
+    },
+    {
+      "epoch": 10.678391959798995,
+      "grad_norm": 9.445945739746094,
+      "learning_rate": 5.368571428571429e-06,
+      "loss": 3.8359,
+      "step": 2125
+    },
+    {
+      "epoch": 10.804020100502512,
+      "grad_norm": 11.811120986938477,
+      "learning_rate": 5.297142857142858e-06,
+      "loss": 3.8632,
+      "step": 2150
+    },
+    {
+      "epoch": 10.92964824120603,
+      "grad_norm": 10.508607864379883,
+      "learning_rate": 5.225714285714286e-06,
+      "loss": 3.8324,
+      "step": 2175
+    },
+    {
+      "epoch": 11.055276381909549,
+      "grad_norm": 8.808614730834961,
+      "learning_rate": 5.154285714285715e-06,
+      "loss": 3.8314,
+      "step": 2200
+    },
+    {
+      "epoch": 11.180904522613066,
+      "grad_norm": 11.709993362426758,
+      "learning_rate": 5.082857142857144e-06,
+      "loss": 3.8904,
+      "step": 2225
+    },
+    {
+      "epoch": 11.306532663316583,
+      "grad_norm": 8.451616287231445,
+      "learning_rate": 5.011428571428571e-06,
+      "loss": 3.8471,
+      "step": 2250
+    },
+    {
+      "epoch": 11.4321608040201,
+      "grad_norm": 10.084294319152832,
+      "learning_rate": 4.94e-06,
+      "loss": 3.8881,
+      "step": 2275
+    },
+    {
+      "epoch": 11.557788944723619,
+      "grad_norm": 17.51856803894043,
+      "learning_rate": 4.868571428571429e-06,
+      "loss": 3.8931,
+      "step": 2300
+    },
+    {
+      "epoch": 11.683417085427136,
+      "grad_norm": 11.671639442443848,
+      "learning_rate": 4.797142857142857e-06,
+      "loss": 3.8578,
+      "step": 2325
+    },
+    {
+      "epoch": 11.809045226130653,
+      "grad_norm": 8.713754653930664,
+      "learning_rate": 4.725714285714286e-06,
+      "loss": 3.832,
+      "step": 2350
+    },
+    {
+      "epoch": 11.93467336683417,
+      "grad_norm": 11.429880142211914,
+      "learning_rate": 4.6542857142857145e-06,
+      "loss": 3.8556,
+      "step": 2375
+    },
+    {
+      "epoch": 12.06030150753769,
+      "grad_norm": 9.178875923156738,
+      "learning_rate": 4.5828571428571435e-06,
+      "loss": 3.8361,
+      "step": 2400
+    },
+    {
+      "epoch": 12.185929648241206,
+      "grad_norm": 7.655440330505371,
+      "learning_rate": 4.511428571428572e-06,
+      "loss": 3.8337,
+      "step": 2425
+    },
+    {
+      "epoch": 12.311557788944723,
+      "grad_norm": 10.44965648651123,
+      "learning_rate": 4.440000000000001e-06,
+      "loss": 3.877,
+      "step": 2450
+    },
+    {
+      "epoch": 12.43718592964824,
+      "grad_norm": 9.04977035522461,
+      "learning_rate": 4.368571428571429e-06,
+      "loss": 3.8504,
+      "step": 2475
+    },
+    {
+      "epoch": 12.56281407035176,
+      "grad_norm": 8.15368366241455,
+      "learning_rate": 4.297142857142858e-06,
+      "loss": 3.8297,
+      "step": 2500
+    },
+    {
+      "epoch": 12.688442211055277,
+      "grad_norm": 9.811213493347168,
+      "learning_rate": 4.225714285714286e-06,
+      "loss": 3.8289,
+      "step": 2525
+    },
+    {
+      "epoch": 12.814070351758794,
+      "grad_norm": 8.397767066955566,
+      "learning_rate": 4.154285714285714e-06,
+      "loss": 3.8352,
+      "step": 2550
+    },
+    {
+      "epoch": 12.93969849246231,
+      "grad_norm": 10.471597671508789,
+      "learning_rate": 4.082857142857143e-06,
+      "loss": 3.8438,
+      "step": 2575
+    },
+    {
+      "epoch": 13.06532663316583,
+      "grad_norm": 8.042658805847168,
+      "learning_rate": 4.011428571428571e-06,
+      "loss": 3.8308,
+      "step": 2600
+    },
+    {
+      "epoch": 13.190954773869347,
+      "grad_norm": 9.240007400512695,
+      "learning_rate": 3.94e-06,
+      "loss": 3.811,
+      "step": 2625
+    },
+    {
+      "epoch": 13.316582914572864,
+      "grad_norm": 8.514374732971191,
+      "learning_rate": 3.8685714285714286e-06,
+      "loss": 3.8253,
+      "step": 2650
+    },
+    {
+      "epoch": 13.442211055276381,
+      "grad_norm": 8.689332008361816,
+      "learning_rate": 3.7971428571428576e-06,
+      "loss": 3.8387,
+      "step": 2675
+    },
+    {
+      "epoch": 13.5678391959799,
+      "grad_norm": 11.250374794006348,
+      "learning_rate": 3.7257142857142857e-06,
+      "loss": 3.8216,
+      "step": 2700
+    },
+    {
+      "epoch": 13.693467336683417,
+      "grad_norm": 8.129416465759277,
+      "learning_rate": 3.6542857142857148e-06,
+      "loss": 3.8273,
+      "step": 2725
+    },
+    {
+      "epoch": 13.819095477386934,
+      "grad_norm": 9.398397445678711,
+      "learning_rate": 3.582857142857143e-06,
+      "loss": 3.8116,
+      "step": 2750
+    },
+    {
+      "epoch": 13.944723618090451,
+      "grad_norm": 9.966887474060059,
+      "learning_rate": 3.511428571428572e-06,
+      "loss": 3.8401,
+      "step": 2775
+    },
+    {
+      "epoch": 14.07035175879397,
+      "grad_norm": 7.829891204833984,
+      "learning_rate": 3.44e-06,
+      "loss": 3.7607,
+      "step": 2800
+    },
+    {
+      "epoch": 14.195979899497488,
+      "grad_norm": 10.33727741241455,
+      "learning_rate": 3.3685714285714287e-06,
+      "loss": 3.8406,
+      "step": 2825
+    },
+    {
+      "epoch": 14.321608040201005,
+      "grad_norm": 8.579668998718262,
+      "learning_rate": 3.2971428571428577e-06,
+      "loss": 3.7893,
+      "step": 2850
+    },
+    {
+      "epoch": 14.447236180904522,
+      "grad_norm": 9.909623146057129,
+      "learning_rate": 3.225714285714286e-06,
+      "loss": 3.8661,
+      "step": 2875
+    },
+    {
+      "epoch": 14.57286432160804,
+      "grad_norm": 9.630623817443848,
+      "learning_rate": 3.154285714285715e-06,
+      "loss": 3.8248,
+      "step": 2900
+    },
+    {
+      "epoch": 14.698492462311558,
+      "grad_norm": 13.711705207824707,
+      "learning_rate": 3.082857142857143e-06,
+      "loss": 3.8268,
+      "step": 2925
+    },
+    {
+      "epoch": 14.824120603015075,
+      "grad_norm": 8.66063117980957,
+      "learning_rate": 3.0114285714285716e-06,
+      "loss": 3.8154,
+      "step": 2950
+    },
+    {
+      "epoch": 14.949748743718594,
+      "grad_norm": 10.465475082397461,
+      "learning_rate": 2.9400000000000002e-06,
+      "loss": 3.826,
+      "step": 2975
+    },
+    {
+      "epoch": 15.075376884422111,
+      "grad_norm": 9.025050163269043,
+      "learning_rate": 2.868571428571429e-06,
+      "loss": 3.8132,
+      "step": 3000
+    },
+    {
+      "epoch": 15.075376884422111,
+      "eval_loss": 0.44469836354255676,
+      "eval_runtime": 78.3312,
+      "eval_samples_per_second": 9.039,
+      "eval_steps_per_second": 4.519,
+      "step": 3000
+    },
+    {
+      "epoch": 15.201005025125628,
+      "grad_norm": 9.333688735961914,
+      "learning_rate": 2.797142857142857e-06,
+      "loss": 3.8107,
+      "step": 3025
+    },
+    {
+      "epoch": 15.326633165829145,
+      "grad_norm": 11.503759384155273,
+      "learning_rate": 2.725714285714286e-06,
+      "loss": 3.8315,
+      "step": 3050
+    },
+    {
+      "epoch": 15.452261306532664,
+      "grad_norm": 10.728011131286621,
+      "learning_rate": 2.654285714285714e-06,
+      "loss": 3.8135,
+      "step": 3075
+    },
+    {
+      "epoch": 15.577889447236181,
+      "grad_norm": 8.355088233947754,
+      "learning_rate": 2.582857142857143e-06,
+      "loss": 3.8079,
+      "step": 3100
+    },
+    {
+      "epoch": 15.703517587939698,
+      "grad_norm": 9.261649131774902,
+      "learning_rate": 2.5114285714285718e-06,
+      "loss": 3.832,
+      "step": 3125
+    },
+    {
+      "epoch": 15.829145728643216,
+      "grad_norm": 7.470139026641846,
+      "learning_rate": 2.4400000000000004e-06,
+      "loss": 3.8065,
+      "step": 3150
+    },
+    {
+      "epoch": 15.954773869346734,
+      "grad_norm": 10.546520233154297,
+      "learning_rate": 2.3685714285714285e-06,
+      "loss": 3.7759,
+      "step": 3175
+    },
+    {
+      "epoch": 16.08040201005025,
+      "grad_norm": 8.22718334197998,
+      "learning_rate": 2.297142857142857e-06,
+      "loss": 3.7758,
+      "step": 3200
+    },
+    {
+      "epoch": 16.20603015075377,
+      "grad_norm": 7.318994045257568,
+      "learning_rate": 2.2257142857142857e-06,
+      "loss": 3.7738,
+      "step": 3225
+    },
+    {
+      "epoch": 16.331658291457288,
+      "grad_norm": 8.533567428588867,
+      "learning_rate": 2.1542857142857147e-06,
+      "loss": 3.7611,
+      "step": 3250
+    },
+    {
+      "epoch": 16.457286432160803,
+      "grad_norm": 12.127696990966797,
+      "learning_rate": 2.0828571428571433e-06,
+      "loss": 3.8306,
+      "step": 3275
+    },
+    {
+      "epoch": 16.582914572864322,
+      "grad_norm": 8.16425609588623,
+      "learning_rate": 2.0114285714285715e-06,
+      "loss": 3.8017,
+      "step": 3300
+    },
+    {
+      "epoch": 16.70854271356784,
+      "grad_norm": 9.96759033203125,
+      "learning_rate": 1.94e-06,
+      "loss": 3.7988,
+      "step": 3325
+    },
+    {
+      "epoch": 16.834170854271356,
+      "grad_norm": 7.703837871551514,
+      "learning_rate": 1.8685714285714289e-06,
+      "loss": 3.8025,
+      "step": 3350
+    },
+    {
+      "epoch": 16.959798994974875,
+      "grad_norm": 9.635499000549316,
+      "learning_rate": 1.7971428571428572e-06,
+      "loss": 3.7641,
+      "step": 3375
+    },
+    {
+      "epoch": 17.08542713567839,
+      "grad_norm": 8.293730735778809,
+      "learning_rate": 1.7257142857142858e-06,
+      "loss": 3.7946,
+      "step": 3400
+    },
+    {
+      "epoch": 17.21105527638191,
+      "grad_norm": 9.113801002502441,
+      "learning_rate": 1.6542857142857144e-06,
+      "loss": 3.7743,
+      "step": 3425
+    },
+    {
+      "epoch": 17.33668341708543,
+      "grad_norm": 12.916595458984375,
+      "learning_rate": 1.582857142857143e-06,
+      "loss": 3.8164,
+      "step": 3450
+    },
+    {
+      "epoch": 17.462311557788944,
+      "grad_norm": 8.181452751159668,
+      "learning_rate": 1.5114285714285714e-06,
+      "loss": 3.7756,
+      "step": 3475
+    },
+    {
+      "epoch": 17.587939698492463,
+      "grad_norm": 9.33465576171875,
+      "learning_rate": 1.44e-06,
+      "loss": 3.7851,
+      "step": 3500
+    },
+    {
+      "epoch": 17.71356783919598,
+      "grad_norm": 9.609382629394531,
+      "learning_rate": 1.3685714285714286e-06,
+      "loss": 3.8087,
+      "step": 3525
+    },
+    {
+      "epoch": 17.839195979899497,
+      "grad_norm": 10.107198715209961,
+      "learning_rate": 1.2971428571428574e-06,
+      "loss": 3.7887,
+      "step": 3550
+    },
+    {
+      "epoch": 17.964824120603016,
+      "grad_norm": 10.769806861877441,
+      "learning_rate": 1.2257142857142857e-06,
+      "loss": 3.8042,
+      "step": 3575
+    },
+    {
+      "epoch": 18.09045226130653,
+      "grad_norm": 9.459657669067383,
+      "learning_rate": 1.1542857142857143e-06,
+      "loss": 3.8038,
+      "step": 3600
+    },
+    {
+      "epoch": 18.21608040201005,
+      "grad_norm": 8.211793899536133,
+      "learning_rate": 1.082857142857143e-06,
+      "loss": 3.7708,
+      "step": 3625
+    },
+    {
+      "epoch": 18.34170854271357,
+      "grad_norm": 6.89067268371582,
+      "learning_rate": 1.0114285714285715e-06,
+      "loss": 3.832,
+      "step": 3650
+    },
+    {
+      "epoch": 18.467336683417084,
+      "grad_norm": 11.42387866973877,
+      "learning_rate": 9.400000000000001e-07,
+      "loss": 3.7837,
+      "step": 3675
+    },
+    {
+      "epoch": 18.592964824120603,
+      "grad_norm": 9.029644012451172,
+      "learning_rate": 8.685714285714286e-07,
+      "loss": 3.7696,
+      "step": 3700
+    },
+    {
+      "epoch": 18.718592964824122,
+      "grad_norm": 7.634586334228516,
+      "learning_rate": 7.971428571428572e-07,
+      "loss": 3.7854,
+      "step": 3725
+    },
+    {
+      "epoch": 18.844221105527637,
+      "grad_norm": 9.12209701538086,
+      "learning_rate": 7.257142857142857e-07,
+      "loss": 3.788,
+      "step": 3750
+    },
+    {
+      "epoch": 18.969849246231156,
+      "grad_norm": 9.065604209899902,
+      "learning_rate": 6.542857142857144e-07,
+      "loss": 3.7881,
+      "step": 3775
+    },
+    {
+      "epoch": 19.09547738693467,
+      "grad_norm": 8.798233032226562,
+      "learning_rate": 5.82857142857143e-07,
+      "loss": 3.8061,
+      "step": 3800
+    },
+    {
+      "epoch": 19.22110552763819,
+      "grad_norm": 7.6765971183776855,
+      "learning_rate": 5.114285714285714e-07,
+      "loss": 3.7917,
+      "step": 3825
+    },
+    {
+      "epoch": 19.34673366834171,
+      "grad_norm": 7.686089992523193,
+      "learning_rate": 4.4e-07,
+      "loss": 3.807,
+      "step": 3850
+    },
+    {
+      "epoch": 19.472361809045225,
+      "grad_norm": 7.45636510848999,
+      "learning_rate": 3.685714285714286e-07,
+      "loss": 3.7984,
+      "step": 3875
+    },
+    {
+      "epoch": 19.597989949748744,
+      "grad_norm": 7.467589378356934,
+      "learning_rate": 2.9714285714285715e-07,
+      "loss": 3.778,
+      "step": 3900
+    },
+    {
+      "epoch": 19.723618090452263,
+      "grad_norm": 14.702427864074707,
+      "learning_rate": 2.2571428571428574e-07,
+      "loss": 3.8033,
+      "step": 3925
+    },
+    {
+      "epoch": 19.849246231155778,
+      "grad_norm": 8.807873725891113,
+      "learning_rate": 1.542857142857143e-07,
+      "loss": 3.7807,
+      "step": 3950
+    },
+    {
+      "epoch": 19.974874371859297,
+      "grad_norm": 8.14664363861084,
+      "learning_rate": 8.285714285714285e-08,
+      "loss": 3.7466,
+      "step": 3975
+    },
+    {
+      "epoch": 20.100502512562816,
+      "grad_norm": 9.232961654663086,
+      "learning_rate": 1.142857142857143e-08,
+      "loss": 3.8105,
+      "step": 4000
+    },
+    {
+      "epoch": 20.100502512562816,
+      "eval_loss": 0.4429960548877716,
+      "eval_runtime": 78.2115,
+      "eval_samples_per_second": 9.052,
+      "eval_steps_per_second": 4.526,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 21,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.800433559026872e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-4000/training_args.bin b/checkpoint-4000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6ccf0404925f6a8a3bda1ade1cb95630a3b1750a
--- /dev/null
+++ b/checkpoint-4000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6ae756af4eb40168228ea5b672dedd9146f11deae4f8d64668e0b2d5a69781
+size 5432
diff --git a/runs/Nov13_08-13-58_bark-train-55585d49f-489fb/events.out.tfevents.1731485639.bark-train-55585d49f-489fb.5894.0 b/runs/Nov13_08-13-58_bark-train-55585d49f-489fb/events.out.tfevents.1731485639.bark-train-55585d49f-489fb.5894.0
new file mode 100644
index 0000000000000000000000000000000000000000..7f53c34033b2b41315b43f84f8e82321c26628df
--- /dev/null
+++ b/runs/Nov13_08-13-58_bark-train-55585d49f-489fb/events.out.tfevents.1731485639.bark-train-55585d49f-489fb.5894.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e77bcfdcfb2aa994f7fbc73c61e3fd5cc967dd8baffadf7606a629c1cb0e26
+size 41825