Initial commit

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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,
+  "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,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "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_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 64,
+  "transformers_version": "4.4.0",
+  "vocab_size": 65
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:635fa64b04534d3fdbfeb0eb056f666a4dc3b69da6b382d04bdebd3c6de38551
+size 2490610183

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "do_normalize": true,
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c1ab6f51758354bce94b889b1117f9a4711fa401a7df791dd81f53366d065b0
+size 1262200343

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f9bbfc662da8015ef424c22600dffce065acb238f887c429fc16defbe58a59
+size 623

trainer_state.json

@@ -0,0 +1,152 @@
+{
+  "best_metric": 0.41098169717138106,
+  "best_model_checkpoint": "/content/wav2vec2-large-xlsr-nepali/checkpoint-2000",
+  "epoch": 34.47863247863248,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 9.4317,
+      "step": 100
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 3.4467,
+      "step": 200
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 0.0002943396226415094,
+      "loss": 3.3566,
+      "step": 300
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 0.00028301886792452826,
+      "loss": 1.9291,
+      "step": 400
+    },
+    {
+      "epoch": 8.62,
+      "learning_rate": 0.00027169811320754714,
+      "loss": 0.7257,
+      "step": 500
+    },
+    {
+      "epoch": 10.34,
+      "learning_rate": 0.000260377358490566,
+      "loss": 0.4447,
+      "step": 600
+    },
+    {
+      "epoch": 12.07,
+      "learning_rate": 0.0002490566037735849,
+      "loss": 0.3317,
+      "step": 700
+    },
+    {
+      "epoch": 13.79,
+      "learning_rate": 0.00023773584905660377,
+      "loss": 0.2567,
+      "step": 800
+    },
+    {
+      "epoch": 15.51,
+      "learning_rate": 0.00022641509433962264,
+      "loss": 0.2293,
+      "step": 900
+    },
+    {
+      "epoch": 17.24,
+      "learning_rate": 0.00021509433962264146,
+      "loss": 0.1675,
+      "step": 1000
+    },
+    {
+      "epoch": 17.24,
+      "eval_loss": 0.3577611744403839,
+      "eval_runtime": 28.2181,
+      "eval_samples_per_second": 7.336,
+      "eval_wer": 0.44869661674986133,
+      "step": 1000
+    },
+    {
+      "epoch": 18.96,
+      "learning_rate": 0.00020377358490566034,
+      "loss": 0.1423,
+      "step": 1100
+    },
+    {
+      "epoch": 20.68,
+      "learning_rate": 0.00019245283018867922,
+      "loss": 0.1365,
+      "step": 1200
+    },
+    {
+      "epoch": 22.41,
+      "learning_rate": 0.0001811320754716981,
+      "loss": 0.1174,
+      "step": 1300
+    },
+    {
+      "epoch": 24.14,
+      "learning_rate": 0.00016981132075471697,
+      "loss": 0.1103,
+      "step": 1400
+    },
+    {
+      "epoch": 25.85,
+      "learning_rate": 0.00015849056603773584,
+      "loss": 0.0915,
+      "step": 1500
+    },
+    {
+      "epoch": 27.58,
+      "learning_rate": 0.0001471698113207547,
+      "loss": 0.0896,
+      "step": 1600
+    },
+    {
+      "epoch": 29.31,
+      "learning_rate": 0.00013584905660377357,
+      "loss": 0.0929,
+      "step": 1700
+    },
+    {
+      "epoch": 31.03,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.075,
+      "step": 1800
+    },
+    {
+      "epoch": 32.75,
+      "learning_rate": 0.00011320754716981132,
+      "loss": 0.0745,
+      "step": 1900
+    },
+    {
+      "epoch": 34.48,
+      "learning_rate": 0.00010188679245283017,
+      "loss": 0.0603,
+      "step": 2000
+    },
+    {
+      "epoch": 34.48,
+      "eval_loss": 0.3987378180027008,
+      "eval_runtime": 27.73,
+      "eval_samples_per_second": 7.465,
+      "eval_wer": 0.41098169717138106,
+      "step": 2000
+    }
+  ],
+  "max_steps": 2900,
+  "num_train_epochs": 50,
+  "total_flos": 9.875307296349696e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97af1403a94c748408eb00b9167fb9e8bade995019b4f065370a98b26f3a6c42
+size 2287