initial commit

config.json

@@ -0,0 +1,86 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ClassificationModel"
+  ],
+  "attention_dropout": 0.075,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "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": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "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,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.075,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.075,
+  "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": 0.0375,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "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": 24,
+  "num_negatives": 100,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d276ebf0b38756b0f782473b78f39f0c39da15d7c4857773cf080c6d968fd3af
+size 2498506121

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": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d338e0fa45a5d33f8c6e7b6e26d2e818465e945c0737ae95012c65508f42c67f
+size 1266147309

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8afc01f2ac5e4eb86a0ff0b975436398db6865230adbb1d4b476009fec0931
+size 14567

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2eaa8858342c99a60bf2ed46bbcfad38113edb439aefeea5d3ce9df3832ab48
+size 623

trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.998331664998331,
+  "global_step": 1870,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.8126709206927986e-06,
+      "loss": 1.792,
+      "step": 374
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.2750904902928595,
+      "eval_f1_score": 0.17558198955755575,
+      "eval_loss": 1.792249083518982,
+      "eval_runtime": 351.3884,
+      "eval_samples_per_second": 8.649,
+      "eval_steps_per_second": 2.163,
+      "step": 374
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.5569735642661806e-06,
+      "loss": 1.7923,
+      "step": 748
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.2750904902928595,
+      "eval_f1_score": 0.15209869477487561,
+      "eval_loss": 1.7973285913467407,
+      "eval_runtime": 349.7493,
+      "eval_samples_per_second": 8.689,
+      "eval_steps_per_second": 2.173,
+      "step": 748
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.3012762078395626e-06,
+      "loss": 1.7867,
+      "step": 1122
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.39486673247778875,
+      "eval_f1_score": 0.1978644849001168,
+      "eval_loss": 1.773677110671997,
+      "eval_runtime": 345.3478,
+      "eval_samples_per_second": 8.8,
+      "eval_steps_per_second": 2.201,
+      "step": 1122
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.0455788514129442e-06,
+      "loss": 1.7681,
+      "step": 1496
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.49950641658440276,
+      "eval_f1_score": 0.21909607145469126,
+      "eval_loss": 1.751068115234375,
+      "eval_runtime": 344.7764,
+      "eval_samples_per_second": 8.814,
+      "eval_steps_per_second": 2.204,
+      "step": 1496
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.7898814949863265e-06,
+      "loss": 1.7286,
+      "step": 1870
+    }
+  ],
+  "max_steps": 4488,
+  "num_train_epochs": 12,
+  "total_flos": 9.102887348352e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9c27d2effedd8fac72ac6241fc92e4f0efdc2775a6678824cc6a97304684d9
+size 2927