init 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": 68,
+  "transformers_version": "4.4.0",
+  "vocab_size": 69
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed0b9aab1b5d4939b3837d0eafb88c9414dc36d03b51d1b481213de99f65398
+size 2490642951

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 sha256:171ae3aec748b1859b2ff82bb47a582e758bf4c7f0aa11dbb61381e0250a29c9
+size 1262216727

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38d1d4d1d0e39a33d7bfef8bc1082ecd1abc1d0342f6a0c947ca5b38bb8689ee
+size 623

trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 21.05263157894737,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 10.53,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 6.4582,
+      "step": 400
+    },
+    {
+      "epoch": 10.53,
+      "eval_loss": 2.820686101913452,
+      "eval_runtime": 541.4545,
+      "eval_samples_per_second": 4.041,
+      "eval_wer": 0.9957617789520036,
+      "step": 400
+    },
+    {
+      "epoch": 21.05,
+      "learning_rate": 0.00015937499999999998,
+      "loss": 0.692,
+      "step": 800
+    },
+    {
+      "epoch": 21.05,
+      "eval_loss": 0.5226749777793884,
+      "eval_runtime": 547.3066,
+      "eval_samples_per_second": 3.998,
+      "eval_wer": 0.41655658300308235,
+      "step": 800
+    }
+  ],
+  "max_steps": 1140,
+  "num_train_epochs": 30,
+  "total_flos": 1.379922511881828e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81db272250312b3f79b8a3f96540f086f35cd461b6951c4799c0ffa6bf4e07eb
+size 2287

vocab.json

@@ -0,0 +1 @@
+{"\u0e37": 0, "\u0e0b": 1, "\u0e06": 2, "\u0e0d": 3, "\u0e07": 4, "\u0e02": 5, "\u0e49": 6, "\u0e2c": 7, "\u0e22": 8, "\u0e16": 9, "\u0e2e": 10, "\u0e2b": 11, "\u0e1b": 12, "\u0e4c": 13, "\u0e35": 14, "\u0e1f": 15, "\u0e1d": 16, "\u0e47": 17, "\u0e2d": 18, "\u0e08": 19, "\u0e0a": 20, "\u0e28": 21, "\u0e34": 22, "\u0e25": 23, "\u0e32": 24, "\u0e1a": 25, "\u0e40": 26, "\u0e29": 27, "\u0e38": 28, "\u0e39": 30, "\u0e36": 31, "\u0e1e": 32, "\u0e04": 33, "\u0e09": 34, "\u0e12": 35, "\u0e15": 36, "\u0e0e": 37, "\u0e10": 38, "\u0e4b": 39, "\u0e46": 40, "\u0e45": 41, "\u0e17": 42, "\u0e41": 43, "\u0e30": 44, "\u0e44": 45, "\u0e01": 46, "\u0e14": 47, "\u0e24": 48, "\u0e31": 49, "\u0e0f": 50, "\u0e20": 51, "\u0e19": 52, "\u0e2a": 53, "\u0e4d": 54, "\u0e43": 55, "\u0e27": 56, "\u0e42": 57, "\u0e33": 58, "\u0e18": 59, "\u0e48": 60, "\u0e21": 61, "\u0e13": 62, "\u0e1c": 63, "\u0e4a": 64, "\u0e11": 65, "\u0e23": 66, "|": 29, "[UNK]": 67, "[PAD]": 68}