Model

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "yip-i/uaspeech-pretrained",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "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": "mean",
+  "ctc_zero_infinity": true,
+  "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": 0.0,
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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_prob": 0.65,
+  "model_type": "wav2vec2",
+  "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": "4.23.1",
+  "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 sha256:92ea1b0eb0e3e05962b98259b3cdad72b6173a32adea95c6544a127bf05128a4
+size 721685265

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:e9eb9734485c631030d3be9199cc999aad0e6d387268b75a87cc681fcd97d315
+size 377702321

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58100b8756b592dcd2a858e2aa15d7a2b9f065faf96fc24aa75d4d39d0a9c57a
+size 14567

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835002e2cdb41a8357f8e813cf9922a361d617175a39e27343c474f97063d4f2
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c1133dea090a0c4005a30006e9f9187f98529135c6396253e9cdc5a2cadb39c
+size 623

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.810572687224669,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.000494,
+      "loss": 6.9554,
+      "step": 500
+    },
+    {
+      "epoch": 2.2,
+      "eval_loss": 3.1107194423675537,
+      "eval_runtime": 13.5928,
+      "eval_samples_per_second": 38.108,
+      "eval_steps_per_second": 9.564,
+      "eval_wer": 1.9065420560747663,
+      "step": 500
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 0.000994,
+      "loss": 3.0727,
+      "step": 1000
+    },
+    {
+      "epoch": 4.41,
+      "eval_loss": 2.740480422973633,
+      "eval_runtime": 13.2579,
+      "eval_samples_per_second": 39.071,
+      "eval_steps_per_second": 9.805,
+      "eval_wer": 1.9457943925233645,
+      "step": 1000
+    },
+    {
+      "epoch": 6.61,
+      "learning_rate": 0.0006110236220472442,
+      "loss": 2.8715,
+      "step": 1500
+    },
+    {
+      "epoch": 6.61,
+      "eval_loss": 2.6221437454223633,
+      "eval_runtime": 12.9721,
+      "eval_samples_per_second": 39.932,
+      "eval_steps_per_second": 10.022,
+      "eval_wer": 1.5046728971962617,
+      "step": 1500
+    },
+    {
+      "epoch": 8.81,
+      "learning_rate": 0.0002173228346456693,
+      "loss": 2.8258,
+      "step": 2000
+    },
+    {
+      "epoch": 8.81,
+      "eval_loss": 2.5607476234436035,
+      "eval_runtime": 13.261,
+      "eval_samples_per_second": 39.062,
+      "eval_steps_per_second": 9.803,
+      "eval_wer": 1.9532710280373833,
+      "step": 2000
+    }
+  ],
+  "max_steps": 2270,
+  "num_train_epochs": 10,
+  "total_flos": 7.015093904496586e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef3b61e993656a96b7c284a7f6260bd52d229ebff8c100bdac03d1239134f19
+size 3375