Upload 13 files

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<ctc_blank>": 80,
+  "<mask>": 79
+}

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": 1876,
+  "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": "4.44.0",
+  "use_cache": false,
+  "use_guided_attention_loss": true,
+  "vocab_size": 81
+}

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": "4.44.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a068d6e39caeacdad2e05f675357c7e88bd7374b050a7196f1edb90e9ba607
+size 577789320

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faa9d11253d4206227f8322ca405fe7e09c3da9b2aee45d2a1eeed0211e1c17e
+size 1155772233

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
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2e0d4e523de01d5b05de2d5350b68daa894b847586d78d93932862182fae946
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba213a4df20c24648758791986d869ac23cc6fe8178b9824db31fd6202f3fe0
+size 1064

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>"
+}

spm_char.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
+size 238473

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": true,
+  "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>"
+}

trainer_state.json

@@ -0,0 +1,213 @@
+{
+  "best_metric": 0.42575815320014954,
+  "best_model_checkpoint": "speecht5_finetuned_bphc/checkpoint-500",
+  "epoch": 2.6595744680851063,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13297872340425532,
+      "grad_norm": 3.7797725200653076,
+      "learning_rate": 2.4e-05,
+      "loss": 1.0695,
+      "step": 25
+    },
+    {
+      "epoch": 0.26595744680851063,
+      "grad_norm": 4.549177169799805,
+      "learning_rate": 4.9e-05,
+      "loss": 0.7576,
+      "step": 50
+    },
+    {
+      "epoch": 0.39893617021276595,
+      "grad_norm": 4.847335338592529,
+      "learning_rate": 7.2e-05,
+      "loss": 0.6571,
+      "step": 75
+    },
+    {
+      "epoch": 0.5319148936170213,
+      "grad_norm": 8.47089958190918,
+      "learning_rate": 9.7e-05,
+      "loss": 0.624,
+      "step": 100
+    },
+    {
+      "epoch": 0.5319148936170213,
+      "eval_loss": 0.5379713177680969,
+      "eval_runtime": 18.8881,
+      "eval_samples_per_second": 35.419,
+      "eval_steps_per_second": 17.736,
+      "step": 100
+    },
+    {
+      "epoch": 0.6648936170212766,
+      "grad_norm": 3.0278241634368896,
+      "learning_rate": 9.449999999999999e-05,
+      "loss": 0.595,
+      "step": 125
+    },
+    {
+      "epoch": 0.7978723404255319,
+      "grad_norm": 4.422701358795166,
+      "learning_rate": 8.825e-05,
+      "loss": 0.5809,
+      "step": 150
+    },
+    {
+      "epoch": 0.9308510638297872,
+      "grad_norm": 4.076521396636963,
+      "learning_rate": 8.2e-05,
+      "loss": 0.5634,
+      "step": 175
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 5.123497009277344,
+      "learning_rate": 7.575e-05,
+      "loss": 0.5563,
+      "step": 200
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "eval_loss": 0.5066816210746765,
+      "eval_runtime": 18.5524,
+      "eval_samples_per_second": 36.06,
+      "eval_steps_per_second": 18.057,
+      "step": 200
+    },
+    {
+      "epoch": 1.196808510638298,
+      "grad_norm": 17.09893226623535,
+      "learning_rate": 6.95e-05,
+      "loss": 0.5311,
+      "step": 225
+    },
+    {
+      "epoch": 1.3297872340425532,
+      "grad_norm": 2.976322889328003,
+      "learning_rate": 6.324999999999999e-05,
+      "loss": 0.5287,
+      "step": 250
+    },
+    {
+      "epoch": 1.4627659574468086,
+      "grad_norm": 2.6360063552856445,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 0.5182,
+      "step": 275
+    },
+    {
+      "epoch": 1.5957446808510638,
+      "grad_norm": 2.318189859390259,
+      "learning_rate": 5.075e-05,
+      "loss": 0.5121,
+      "step": 300
+    },
+    {
+      "epoch": 1.5957446808510638,
+      "eval_loss": 0.46897533535957336,
+      "eval_runtime": 18.3638,
+      "eval_samples_per_second": 36.43,
+      "eval_steps_per_second": 18.242,
+      "step": 300
+    },
+    {
+      "epoch": 1.728723404255319,
+      "grad_norm": 4.144455909729004,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 0.5006,
+      "step": 325
+    },
+    {
+      "epoch": 1.8617021276595744,
+      "grad_norm": 3.1114983558654785,
+      "learning_rate": 3.825e-05,
+      "loss": 0.493,
+      "step": 350
+    },
+    {
+      "epoch": 1.9946808510638299,
+      "grad_norm": 4.484862804412842,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.4862,
+      "step": 375
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 7.771288871765137,
+      "learning_rate": 2.5750000000000002e-05,
+      "loss": 0.4795,
+      "step": 400
+    },
+    {
+      "epoch": 2.127659574468085,
+      "eval_loss": 0.4404144883155823,
+      "eval_runtime": 18.5295,
+      "eval_samples_per_second": 36.105,
+      "eval_steps_per_second": 18.079,
+      "step": 400
+    },
+    {
+      "epoch": 2.2606382978723403,
+      "grad_norm": 3.972978115081787,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.478,
+      "step": 425
+    },
+    {
+      "epoch": 2.393617021276596,
+      "grad_norm": 4.415282726287842,
+      "learning_rate": 1.3250000000000002e-05,
+      "loss": 0.4722,
+      "step": 450
+    },
+    {
+      "epoch": 2.526595744680851,
+      "grad_norm": 3.901869773864746,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 0.4623,
+      "step": 475
+    },
+    {
+      "epoch": 2.6595744680851063,
+      "grad_norm": 6.222782135009766,
+      "learning_rate": 7.5e-07,
+      "loss": 0.4622,
+      "step": 500
+    },
+    {
+      "epoch": 2.6595744680851063,
+      "eval_loss": 0.42575815320014954,
+      "eval_runtime": 18.6784,
+      "eval_samples_per_second": 35.817,
+      "eval_steps_per_second": 17.935,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1478228411981376.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1148b1912964d29456782fe661d5e9d5c4b2a3310bca47f1a58924e264869da0
+size 5368