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": 29,
+  "transformers_version": "4.5.0.dev0",
+  "vocab_size": 30
+}

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 sha256:5b98f47bd4e856a0aba2d9c189725c0c8a895b2e4d32bd5cb1a154878af17d31
+size 1262056855

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|"}

trainer_state.json

@@ -0,0 +1,254 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 28.93617021276596,
+  "global_step": 6800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 4.3481,
+      "step": 400
+    },
+    {
+      "epoch": 1.7,
+      "eval_loss": 2.619910955429077,
+      "eval_runtime": 671.3151,
+      "eval_samples_per_second": 7.704,
+      "eval_wer": 0.99997385142379,
+      "step": 400
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 0.00028625954198473283,
+      "loss": 0.5343,
+      "step": 800
+    },
+    {
+      "epoch": 3.4,
+      "eval_loss": 0.27097710967063904,
+      "eval_runtime": 691.1513,
+      "eval_samples_per_second": 7.483,
+      "eval_wer": 0.4792511047773449,
+      "step": 800
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 0.0002679389312977099,
+      "loss": 0.1541,
+      "step": 1200
+    },
+    {
+      "epoch": 5.11,
+      "eval_loss": 0.2556667923927307,
+      "eval_runtime": 706.9613,
+      "eval_samples_per_second": 7.316,
+      "eval_wer": 0.44368904113171037,
+      "step": 1200
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 0.00024961832061068704,
+      "loss": 0.1049,
+      "step": 1600
+    },
+    {
+      "epoch": 6.81,
+      "eval_loss": 0.23636971414089203,
+      "eval_runtime": 720.2903,
+      "eval_samples_per_second": 7.18,
+      "eval_wer": 0.4181680307507256,
+      "step": 1600
+    },
+    {
+      "epoch": 8.51,
+      "learning_rate": 0.0002312977099236641,
+      "loss": 0.0867,
+      "step": 2000
+    },
+    {
+      "epoch": 8.51,
+      "eval_loss": 0.24546758830547333,
+      "eval_runtime": 728.0447,
+      "eval_samples_per_second": 7.104,
+      "eval_wer": 0.40582590277959363,
+      "step": 2000
+    },
+    {
+      "epoch": 10.21,
+      "learning_rate": 0.0002129770992366412,
+      "loss": 0.0696,
+      "step": 2400
+    },
+    {
+      "epoch": 10.21,
+      "eval_loss": 0.26230543851852417,
+      "eval_runtime": 725.2392,
+      "eval_samples_per_second": 7.131,
+      "eval_wer": 0.3916272258975499,
+      "step": 2400
+    },
+    {
+      "epoch": 11.91,
+      "learning_rate": 0.0001946564885496183,
+      "loss": 0.0637,
+      "step": 2800
+    },
+    {
+      "epoch": 11.91,
+      "eval_loss": 0.2552664577960968,
+      "eval_runtime": 729.1761,
+      "eval_samples_per_second": 7.093,
+      "eval_wer": 0.3940067463326622,
+      "step": 2800
+    },
+    {
+      "epoch": 13.62,
+      "learning_rate": 0.0001763358778625954,
+      "loss": 0.0554,
+      "step": 3200
+    },
+    {
+      "epoch": 13.62,
+      "eval_loss": 0.24944408237934113,
+      "eval_runtime": 725.5889,
+      "eval_samples_per_second": 7.128,
+      "eval_wer": 0.3822660356143608,
+      "step": 3200
+    },
+    {
+      "epoch": 15.32,
+      "learning_rate": 0.0001580152671755725,
+      "loss": 0.0477,
+      "step": 3600
+    },
+    {
+      "epoch": 15.32,
+      "eval_loss": 0.25511008501052856,
+      "eval_runtime": 714.9627,
+      "eval_samples_per_second": 7.234,
+      "eval_wer": 0.38171691551395026,
+      "step": 3600
+    },
+    {
+      "epoch": 17.02,
+      "learning_rate": 0.0001396946564885496,
+      "loss": 0.0441,
+      "step": 4000
+    },
+    {
+      "epoch": 17.02,
+      "eval_loss": 0.26531100273132324,
+      "eval_runtime": 724.9275,
+      "eval_samples_per_second": 7.135,
+      "eval_wer": 0.3808540124990194,
+      "step": 4000
+    },
+    {
+      "epoch": 18.72,
+      "learning_rate": 0.00012137404580152671,
+      "loss": 0.0414,
+      "step": 4400
+    },
+    {
+      "epoch": 18.72,
+      "eval_loss": 0.2718845307826996,
+      "eval_runtime": 724.6581,
+      "eval_samples_per_second": 7.137,
+      "eval_wer": 0.3761211202050048,
+      "step": 4400
+    },
+    {
+      "epoch": 20.43,
+      "learning_rate": 0.00010305343511450381,
+      "loss": 0.0364,
+      "step": 4800
+    },
+    {
+      "epoch": 20.43,
+      "eval_loss": 0.2734206020832062,
+      "eval_runtime": 721.5427,
+      "eval_samples_per_second": 7.168,
+      "eval_wer": 0.36911330178071805,
+      "step": 4800
+    },
+    {
+      "epoch": 22.13,
+      "learning_rate": 8.473282442748092e-05,
+      "loss": 0.0345,
+      "step": 5200
+    },
+    {
+      "epoch": 22.13,
+      "eval_loss": 0.2777670919895172,
+      "eval_runtime": 750.8687,
+      "eval_samples_per_second": 6.888,
+      "eval_wer": 0.3657924326020448,
+      "step": 5200
+    },
+    {
+      "epoch": 23.83,
+      "learning_rate": 6.641221374045802e-05,
+      "loss": 0.0304,
+      "step": 5600
+    },
+    {
+      "epoch": 23.83,
+      "eval_loss": 0.2627178430557251,
+      "eval_runtime": 737.7059,
+      "eval_samples_per_second": 7.011,
+      "eval_wer": 0.36197474047538114,
+      "step": 5600
+    },
+    {
+      "epoch": 25.53,
+      "learning_rate": 4.809160305343511e-05,
+      "loss": 0.028,
+      "step": 6000
+    },
+    {
+      "epoch": 25.53,
+      "eval_loss": 0.2723003923892975,
+      "eval_runtime": 739.1125,
+      "eval_samples_per_second": 6.998,
+      "eval_wer": 0.3572156996051565,
+      "step": 6000
+    },
+    {
+      "epoch": 27.23,
+      "learning_rate": 2.977099236641221e-05,
+      "loss": 0.0257,
+      "step": 6400
+    },
+    {
+      "epoch": 27.23,
+      "eval_loss": 0.2800405025482178,
+      "eval_runtime": 740.691,
+      "eval_samples_per_second": 6.983,
+      "eval_wer": 0.353633344664383,
+      "step": 6400
+    },
+    {
+      "epoch": 28.94,
+      "learning_rate": 1.1450381679389312e-05,
+      "loss": 0.0257,
+      "step": 6800
+    },
+    {
+      "epoch": 28.94,
+      "eval_loss": 0.27684447169303894,
+      "eval_runtime": 742.5074,
+      "eval_samples_per_second": 6.966,
+      "eval_wer": 0.35324111602123265,
+      "step": 6800
+    }
+  ],
+  "max_steps": 7050,
+  "num_train_epochs": 30,
+  "total_flos": 3.4777475593836667e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b94ada224cd956051c3a9d3dc97df0e3932dbb6f2377daa0bc80f35798c77e01
+size 2287

vocab.json

@@ -0,0 +1 @@
+{"q": 0, "b": 1, "r": 2, "h": 4, "j": 5, "f": 6, "a": 7, "u": 8, "x": 9, "p": 10, "w": 11, "z": 12, "k": 13, "e": 14, "l": 15, "y": 16, "t": 17, "g": 18, "c": 19, "d": 20, "o": 21, "n": 22, "ñ": 23, "v": 24, "m": 25, "s": 26, "i": 27, "|": 3, "[UNK]": 28, "[PAD]": 29}