Upload 13 files

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 30, "</s>": 31}

config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "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": 256,
+  "contrastive_logits_temperature": 0.1,
+  "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
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "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": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 29,
+  "proj_codevector_dim": 256,
+  "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": "4.17.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d44a61c59e674ab742d7365855aa6fd69ee86bc0df246cffdda3e1a5a05fc67b
+size 755296058

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23adeff6ac4d75df46711232bd2e4e009f0e866b3819e317b4c0bc3bdd43650b
+size 377673950

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d82838f933ee9c573fe25acaf5dd03904ec57b868eef0f301fc7c5b6449f930e
+size 14308

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99be617058bc65f9146641e4f30d18c525cd81a4e02f37f04bcf43ecba9e598d
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e675137f2f7083fb3c7e467df7f1ebc1a1ea8e2f58efd105df9b55f748fe5496
+size 1064

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false}]}

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": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 24.0,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 3.554,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.8209362030029297,
+      "eval_runtime": 59.6048,
+      "eval_samples_per_second": 28.186,
+      "eval_steps_per_second": 3.523,
+      "eval_wer": 1.027634208531459,
+      "step": 500
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 9.95e-05,
+      "loss": 0.6528,
+      "step": 1000
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.45033037662506104,
+      "eval_runtime": 59.343,
+      "eval_samples_per_second": 28.31,
+      "eval_steps_per_second": 3.539,
+      "eval_wer": 0.438632761353456,
+      "step": 1000
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 8.2e-05,
+      "loss": 0.2126,
+      "step": 1500
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.4427516460418701,
+      "eval_runtime": 58.1542,
+      "eval_samples_per_second": 28.889,
+      "eval_steps_per_second": 3.611,
+      "eval_wer": 0.3861208738198608,
+      "step": 1500
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 6.381818181818183e-05,
+      "loss": 0.122,
+      "step": 2000
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 0.443359375,
+      "eval_runtime": 60.2568,
+      "eval_samples_per_second": 27.881,
+      "eval_steps_per_second": 3.485,
+      "eval_wer": 0.37357866446144306,
+      "step": 2000
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 4.567272727272727e-05,
+      "loss": 0.083,
+      "step": 2500
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 0.46422243118286133,
+      "eval_runtime": 59.9224,
+      "eval_samples_per_second": 28.036,
+      "eval_steps_per_second": 3.505,
+      "eval_wer": 0.35331817242092206,
+      "step": 2500
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 2.7490909090909094e-05,
+      "loss": 0.0614,
+      "step": 3000
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 0.4522028863430023,
+      "eval_runtime": 60.7885,
+      "eval_samples_per_second": 27.637,
+      "eval_steps_per_second": 3.455,
+      "eval_wer": 0.34635793535938253,
+      "step": 3000
+    }
+  ],
+  "max_steps": 3750,
+  "num_train_epochs": 30,
+  "total_flos": 2.4789473171977364e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63764cd0ea8f9bbfc71d358477aea28e99a40374d50b3d562bc362042784b3d5
+size 3512

vocab.json

@@ -0,0 +1 @@
+{"'": 0, "w": 1, "u": 2, "b": 3, "e": 4, "s": 5, "l": 6, "i": 7, "v": 8, "m": 9, "n": 10, "g": 11, "z": 12, "c": 13, "t": 14, "d": 15, "p": 16, "y": 17, "x": 18, "j": 19, "f": 20, "r": 21, "k": 22, "h": 24, "o": 25, "a": 26, "q": 27, "|": 23, "[UNK]": 28, "[PAD]": 29}