Upload 8 files

config.json

@@ -0,0 +1,116 @@
+{
+  "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": 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": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "dtype": "float32",
+  "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,
+  "gradient_checkpointing": false,
+  "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_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",
+  "num_adapter_layers": 3,
+  "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,
+  "output_hidden_size": 1024,
+  "pad_token_id": 96,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "transformers_version": "4.57.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 99,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e128cb233dafb4551e3472c74e68ea4b60552db16c58e529bc334640c66097
+size 1262213380

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430c1d1cac9df35415f4da6425a2f985951c53c15ebc3b27c66b5c558c6b124a
+size 2490977543

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc4bb84af9f1e318d22f027e48a9e86b0e5177ee0752f134ecb35962ce908664
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc6badeb41b78c0eecd119dff15b55402797c86111a648f27fc8d02c5d0b6f3
+size 1465

trainer_state.json

@@ -0,0 +1,162 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 22.857142857142858,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 2.1410279273986816,
+      "learning_rate": 0.0002830285714285714,
+      "loss": 5.8301,
+      "step": 100
+    },
+    {
+      "epoch": 2.857142857142857,
+      "eval_loss": Infinity,
+      "eval_runtime": 253.3004,
+      "eval_samples_per_second": 4.015,
+      "eval_steps_per_second": 0.505,
+      "eval_wer": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 1.1604962348937988,
+      "learning_rate": 0.00026588571428571423,
+      "loss": 3.4386,
+      "step": 200
+    },
+    {
+      "epoch": 5.714285714285714,
+      "eval_loss": Infinity,
+      "eval_runtime": 243.6608,
+      "eval_samples_per_second": 4.174,
+      "eval_steps_per_second": 0.525,
+      "eval_wer": 1.0,
+      "step": 200
+    },
+    {
+      "epoch": 8.571428571428571,
+      "grad_norm": 0.4299349784851074,
+      "learning_rate": 0.0002487428571428571,
+      "loss": 3.3685,
+      "step": 300
+    },
+    {
+      "epoch": 8.571428571428571,
+      "eval_loss": Infinity,
+      "eval_runtime": 247.936,
+      "eval_samples_per_second": 4.102,
+      "eval_steps_per_second": 0.516,
+      "eval_wer": 1.0,
+      "step": 300
+    },
+    {
+      "epoch": 11.428571428571429,
+      "grad_norm": 1.2668368816375732,
+      "learning_rate": 0.0002316,
+      "loss": 3.273,
+      "step": 400
+    },
+    {
+      "epoch": 11.428571428571429,
+      "eval_loss": Infinity,
+      "eval_runtime": 248.6637,
+      "eval_samples_per_second": 4.09,
+      "eval_steps_per_second": 0.515,
+      "eval_wer": 1.000101389029707,
+      "step": 400
+    },
+    {
+      "epoch": 14.285714285714286,
+      "grad_norm": 0.6865704655647278,
+      "learning_rate": 0.00021445714285714285,
+      "loss": 2.3959,
+      "step": 500
+    },
+    {
+      "epoch": 14.285714285714286,
+      "eval_loss": Infinity,
+      "eval_runtime": 247.7757,
+      "eval_samples_per_second": 4.105,
+      "eval_steps_per_second": 0.517,
+      "eval_wer": 1.0419750582986922,
+      "step": 500
+    },
+    {
+      "epoch": 17.142857142857142,
+      "grad_norm": 0.8751232624053955,
+      "learning_rate": 0.0001973142857142857,
+      "loss": 0.8573,
+      "step": 600
+    },
+    {
+      "epoch": 17.142857142857142,
+      "eval_loss": Infinity,
+      "eval_runtime": 243.8476,
+      "eval_samples_per_second": 4.171,
+      "eval_steps_per_second": 0.525,
+      "eval_wer": 0.9248707289871236,
+      "step": 600
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.9577571153640747,
+      "learning_rate": 0.00018017142857142856,
+      "loss": 0.4297,
+      "step": 700
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": Infinity,
+      "eval_runtime": 244.1643,
+      "eval_samples_per_second": 4.165,
+      "eval_steps_per_second": 0.524,
+      "eval_wer": 0.8859373415796411,
+      "step": 700
+    },
+    {
+      "epoch": 22.857142857142858,
+      "grad_norm": 0.5534085035324097,
+      "learning_rate": 0.00016302857142857144,
+      "loss": 0.302,
+      "step": 800
+    },
+    {
+      "epoch": 22.857142857142858,
+      "eval_loss": Infinity,
+      "eval_runtime": 246.7635,
+      "eval_samples_per_second": 4.121,
+      "eval_steps_per_second": 0.519,
+      "eval_wer": 0.8783331643516171,
+      "step": 800
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.939722461016017e+18,
+  "train_batch_size": 30,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7ae28f3055f49d87823062a3558f75dedb7f93dfaa6a85a9b2fa848dee4042
+size 5777