Upload 8 files

config.json

@@ -0,0 +1,118 @@
+{
+  "_name_or_path": "/workspace/ASR/models/pre_train/output/model_output/checkpoint-396800",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "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": 0.0,
+  "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": 0.1,
+  "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_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": 0,
+  "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": "4.30.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 11176,
+  "xvector_output_dim": 512
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:434e0afeb1e9f3e6640c533e1329c9b5294d533bd991ca6eade5eed07881a01e
+size 95134

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 sha256:8b5a4bcc5965a2604fec41f76421420f13e72fff794f97fce361ae7bfcbd6b8d
+size 411938142

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78162b8ba4502785eb81bfa3189ddc9f4bfefd5a1fc80acd4d5d5f0234a70f50
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cd4fa9ffac72f0c71e50470cc07ce7d8abc795c39bfaaa9f83bfed7b151e4b4
+size 1064

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 201.0846405029297,
+  "best_model_checkpoint": "./output/model_output/checkpoint-2000",
+  "epoch": 0.06526882597699274,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.820000000000001e-06,
+      "loss": 340.5683,
+      "step": 500
+    },
+    {
+      "epoch": 0.02,
+      "eval_CER": 5.084942084942085,
+      "eval_loss": 333.91064453125,
+      "eval_runtime": 0.3435,
+      "eval_samples_per_second": 29.111,
+      "eval_steps_per_second": 8.733,
+      "step": 500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.999936439679716e-06,
+      "loss": 306.7755,
+      "step": 1000
+    },
+    {
+      "epoch": 0.03,
+      "eval_CER": 0.7760617760617761,
+      "eval_loss": 294.28277587890625,
+      "eval_runtime": 0.3348,
+      "eval_samples_per_second": 29.865,
+      "eval_steps_per_second": 8.959,
+      "step": 1000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.999741601099537e-06,
+      "loss": 291.7735,
+      "step": 1500
+    },
+    {
+      "epoch": 0.05,
+      "eval_CER": 1.0,
+      "eval_loss": 248.63803100585938,
+      "eval_runtime": 0.3203,
+      "eval_samples_per_second": 31.222,
+      "eval_steps_per_second": 9.367,
+      "step": 1500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.999414687126431e-06,
+      "loss": 237.9951,
+      "step": 2000
+    },
+    {
+      "epoch": 0.07,
+      "eval_CER": 1.0,
+      "eval_loss": 201.0846405029297,
+      "eval_runtime": 0.3248,
+      "eval_samples_per_second": 30.789,
+      "eval_steps_per_second": 9.237,
+      "step": 2000
+    }
+  ],
+  "max_steps": 306420,
+  "num_train_epochs": 10,
+  "total_flos": 1.648747520322154e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b646b5e728a9423da27aa9a15e415e7f6a3088a48355d3ae8425bddd988c7df
+size 4344