add arabic model

config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "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_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 36,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 37,
+  "xvector_output_dim": 512
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a5438caadb5af2ea933c1de94f3f9950ee0f6b97b5180f36d651fdd88509463
+size 2490362385

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5406885859307fbe939245dbb86c7e555b0b4368e461de18e55edc97b0a4cefa
+size 1262075377

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf64fb7b54a451590e26f6c04910ceee2c3ce27d9e1b6166c4789f4625fa1dfb
+size 14567

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fadfa6df2e109e3163e54674a5cfaf0521decee799dcc360823a398ffc8a721
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17021d32677a589959577db7e07f1a6f6cc4f5853ac51662013d08420c040379
+size 623

trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.30232558139535,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.1,
+      "learning_rate": 7.920000000000001e-05,
+      "loss": 9.9787,
+      "step": 400
+    },
+    {
+      "epoch": 3.1,
+      "eval_loss": 3.0419623851776123,
+      "eval_runtime": 81.9377,
+      "eval_samples_per_second": 23.323,
+      "eval_steps_per_second": 2.917,
+      "eval_wer": 1.0,
+      "step": 400
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 6.253164556962025e-05,
+      "loss": 2.7264,
+      "step": 800
+    },
+    {
+      "epoch": 6.2,
+      "eval_loss": 1.3224282264709473,
+      "eval_runtime": 81.6615,
+      "eval_samples_per_second": 23.401,
+      "eval_steps_per_second": 2.927,
+      "eval_wer": 1.067686658506732,
+      "step": 800
+    },
+    {
+      "epoch": 9.3,
+      "learning_rate": 1.189873417721519e-05,
+      "loss": 0.9607,
+      "step": 1200
+    },
+    {
+      "epoch": 9.3,
+      "eval_loss": 0.6051472425460815,
+      "eval_runtime": 80.842,
+      "eval_samples_per_second": 23.639,
+      "eval_steps_per_second": 2.956,
+      "eval_wer": 0.7376988984088128,
+      "step": 1200
+    }
+  ],
+  "max_steps": 1290,
+  "num_train_epochs": 10,
+  "total_flos": 4.3671042896313257e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac244823f4a70e3609083f010fe13184f4bc0082f7aa9603beda9a2337ee36c1
+size 3183

vocab.json

@@ -0,0 +1 @@
+{"\u0628": 0, "\u0626": 1, "\u0631": 2, "\u062a": 3, "\u062f": 4, "\u0646": 5, "\u063a": 6, "\u0634": 7, "\u0642": 8, "\u0647": 9, "\u064a": 10, "\u0629": 11, "\u0638": 12, "\u062b": 13, "\u0630": 14, "\u0641": 15, "\u0635": 17, "\u0639": 18, "\u0633": 19, "\u0648": 20, "\u062c": 21, "\u0645": 22, "\u0624": 23, "\u0632": 24, "\u0644": 25, "\u0627": 26, "\u0649": 27, "\u0621": 28, "\u062e": 29, "\u06cc": 30, "\u0643": 31, "\u0637": 32, "\u062d": 33, "\u0636": 34, "|": 16, "[UNK]": 35, "[PAD]": 36}