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": 46,
+  "transformers_version": "4.4.0",
+  "vocab_size": 47
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:419f5d800dc0440d5bbd40b757e6cba559b6071aca0458843c39ebd28963d8ea
+size 2490462599

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 sha256:4f919a7b5fe74ce903f06d7748c5d9136e2210fc15d0c9a879d88d0ec50dc500
+size 1262126551

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d935e5341553adff3f2b55a147839deb34f34f235c9b036001599117860fabc8
+size 623

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 +1,86 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 50.0,
+  "global_step": 2750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0003,
+      "loss": 4.1674,
+      "step": 550
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.8416548371315002,
+      "eval_runtime": 101.0995,
+      "eval_samples_per_second": 7.794,
+      "eval_wer": 0.8985163204747775,
+      "step": 550
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 0.000225,
+      "loss": 0.3273,
+      "step": 1100
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 0.6257408857345581,
+      "eval_runtime": 102.9185,
+      "eval_samples_per_second": 7.657,
+      "eval_wer": 0.6571711177052423,
+      "step": 1100
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 0.00015,
+      "loss": 0.1125,
+      "step": 1650
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 0.709644615650177,
+      "eval_runtime": 103.3162,
+      "eval_samples_per_second": 7.627,
+      "eval_wer": 0.6631058358061326,
+      "step": 1650
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 7.5e-05,
+      "loss": 0.0718,
+      "step": 2200
+    },
+    {
+      "epoch": 40.0,
+      "eval_loss": 0.7290266156196594,
+      "eval_runtime": 109.3818,
+      "eval_samples_per_second": 7.204,
+      "eval_wer": 0.6189910979228487,
+      "step": 2200
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 0.0,
+      "loss": 0.0551,
+      "step": 2750
+    },
+    {
+      "epoch": 50.0,
+      "eval_loss": 0.7108353972434998,
+      "eval_runtime": 106.4037,
+      "eval_samples_per_second": 7.406,
+      "eval_wer": 0.6126607319485657,
+      "step": 2750
+    }
+  ],
+  "max_steps": 2750,
+  "num_train_epochs": 50,
+  "total_flos": 1.1543543816112128e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0dce15ceaef577857918acb8183edca48ef839effa6741c1d2551a0b3422621
+size 2287

vocab.json

@@ -0,0 +1 @@
+{"ц": 0, "з": 1, "щ": 2, "и": 3, "к": 4, "р": 5, "ь": 6, "ç": 7, "т": 8, "ĕ": 9, "а": 10, "х": 11, "ӗ": 12, "—": 13, "й": 14, "г": 15, "э": 16, "п": 17, "я": 18, "с": 19, "в": 20, "ӳ": 21, "ӑ": 22, "о": 23, "б": 24, "ф": 25, "ъ": 26, "у": 27, "–": 28, "ҫ": 29, "ы": 30, "д": 31, "е": 32, "н": 33, "ш": 34, "ч": 35, "»": 36, "«": 37, "ю": 38, "ж": 39, "ă": 41, "м": 42, "…": 43, "л": 44, "|": 40, "[UNK]": 45, "[PAD]": 46}