diff --git a/.ipynb_checkpoints/config-checkpoint.json b/.ipynb_checkpoints/config-checkpoint.json
new file mode 100644
index 0000000000000000000000000000000000000000..ce6afb5abdb755f8a3c760398662bbeb930c6cef
--- /dev/null
+++ b/.ipynb_checkpoints/config-checkpoint.json
@@ -0,0 +1,118 @@
+{
+ "_name_or_path": "facebook/wav2vec2-base",
+ "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": 0.1,
+ "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": 0.0,
+ "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": 28,
+ "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": "4.41.1",
+ "use_weighted_layer_sum": false,
+ "vocab_size": 32,
+ "xvector_output_dim": 512
+}
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..8853dc9846b128287aafe9d49357df6f77736a53
--- /dev/null
+++ b/README.md
@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: results
+ results: []
+---
+
+
+
+# results
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.0314
+- Wer: 1.0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer |
+|:-------------:|:-------:|:----:|:---------------:|:---:|
+| 2.8609 | 5.7143 | 1000 | 3.1199 | 1.0 |
+| 2.8589 | 11.4286 | 2000 | 3.0515 | 1.0 |
+| 2.8587 | 17.1429 | 3000 | 2.9922 | 1.0 |
+| 2.856 | 22.8571 | 4000 | 3.0177 | 1.0 |
+| 2.8531 | 28.5714 | 5000 | 3.0314 | 1.0 |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1
diff --git a/added_tokens.json b/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..cc95e40ec61ca6dc6f02948ceaad78a75e854f3f
--- /dev/null
+++ b/added_tokens.json
@@ -0,0 +1,4 @@
+{
+ "": 30,
+ "": 29
+}
diff --git a/checkpoint-3000/added_tokens.json b/checkpoint-3000/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..cc95e40ec61ca6dc6f02948ceaad78a75e854f3f
--- /dev/null
+++ b/checkpoint-3000/added_tokens.json
@@ -0,0 +1,4 @@
+{
+ "": 30,
+ "": 29
+}
diff --git a/checkpoint-3000/config.json b/checkpoint-3000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ce6afb5abdb755f8a3c760398662bbeb930c6cef
--- /dev/null
+++ b/checkpoint-3000/config.json
@@ -0,0 +1,118 @@
+{
+ "_name_or_path": "facebook/wav2vec2-base",
+ "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": 0.1,
+ "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": 0.0,
+ "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": 28,
+ "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": "4.41.1",
+ "use_weighted_layer_sum": false,
+ "vocab_size": 32,
+ "xvector_output_dim": 512
+}
diff --git a/checkpoint-3000/model.safetensors b/checkpoint-3000/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2a7edee2ec057d50a3bedc6e76095eaf96a8311e
--- /dev/null
+++ b/checkpoint-3000/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3057d96dc780ed10a08e0805f8894f3be2fd687c40e169bcad108bc23c858b17
+size 377611120
diff --git a/checkpoint-3000/optimizer.pt b/checkpoint-3000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e012382c8946319e95450cd9188ff7d3f390005f
--- /dev/null
+++ b/checkpoint-3000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb37c540edf376ce6a31ec0d63fd8890e0d7e577cac31a576fec618f977b03e
+size 755348794
diff --git a/checkpoint-3000/preprocessor_config.json b/checkpoint-3000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c626b5517871d529f0ed94aded16d875d0dd4ea2
--- /dev/null
+++ b/checkpoint-3000/preprocessor_config.json
@@ -0,0 +1,10 @@
+{
+ "do_normalize": true,
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+ "feature_size": 1,
+ "padding_side": "right",
+ "padding_value": 0.0,
+ "processor_class": "Wav2Vec2Processor",
+ "return_attention_mask": false,
+ "sampling_rate": 16000
+}
diff --git a/checkpoint-3000/rng_state.pth b/checkpoint-3000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6e95183e6f73645ad4f9738764d71949c15eeb43
--- /dev/null
+++ b/checkpoint-3000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f0a16b818a012c97aab56f895a95a490bff11514b9c74acf7d1222b2c806984
+size 14308
diff --git a/checkpoint-3000/scheduler.pt b/checkpoint-3000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fe4b7d71d276e43f3b9257a08b9adc906c62e366
--- /dev/null
+++ b/checkpoint-3000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:657dc5b82fa7223b420413a7de9e568ab43580637ab10908da5c9162475c8968
+size 1064
diff --git a/checkpoint-3000/special_tokens_map.json b/checkpoint-3000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..7f1669a2a2a16dae6adcf40b222f836ed75cbd1e
--- /dev/null
+++ b/checkpoint-3000/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "[PAD]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "[UNK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ }
+}
diff --git a/checkpoint-3000/tokenizer_config.json b/checkpoint-3000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa10530c450758d82ee7c9c929838cf2ba1ac18e
--- /dev/null
+++ b/checkpoint-3000/tokenizer_config.json
@@ -0,0 +1,48 @@
+{
+ "added_tokens_decoder": {
+ "27": {
+ "content": "[UNK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "28": {
+ "content": "[PAD]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "29": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "30": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "",
+ "clean_up_tokenization_spaces": true,
+ "do_lower_case": false,
+ "eos_token": "",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "[PAD]",
+ "processor_class": "Wav2Vec2Processor",
+ "replace_word_delimiter_char": " ",
+ "target_lang": null,
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
+ "unk_token": "[UNK]",
+ "word_delimiter_token": "|"
+}
diff --git a/checkpoint-3000/trainer_state.json b/checkpoint-3000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..88570082dcf8651e7f28c5fc96432171f320897a
--- /dev/null
+++ b/checkpoint-3000/trainer_state.json
@@ -0,0 +1,102 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 17.142857142857142,
+ "eval_steps": 1000,
+ "global_step": 3000,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 2.857142857142857,
+ "grad_norm": 0.991371750831604,
+ "learning_rate": 9.8e-05,
+ "loss": 3.541,
+ "step": 500
+ },
+ {
+ "epoch": 5.714285714285714,
+ "grad_norm": 0.3066103756427765,
+ "learning_rate": 8.96842105263158e-05,
+ "loss": 2.8609,
+ "step": 1000
+ },
+ {
+ "epoch": 5.714285714285714,
+ "eval_loss": 3.1199309825897217,
+ "eval_runtime": 29.6116,
+ "eval_samples_per_second": 23.639,
+ "eval_steps_per_second": 2.972,
+ "eval_wer": 1.0,
+ "step": 1000
+ },
+ {
+ "epoch": 8.571428571428571,
+ "grad_norm": 0.7332219481468201,
+ "learning_rate": 7.915789473684211e-05,
+ "loss": 2.8625,
+ "step": 1500
+ },
+ {
+ "epoch": 11.428571428571429,
+ "grad_norm": 0.29804107546806335,
+ "learning_rate": 6.863157894736843e-05,
+ "loss": 2.8589,
+ "step": 2000
+ },
+ {
+ "epoch": 11.428571428571429,
+ "eval_loss": 3.051466941833496,
+ "eval_runtime": 29.5006,
+ "eval_samples_per_second": 23.728,
+ "eval_steps_per_second": 2.983,
+ "eval_wer": 1.0,
+ "step": 2000
+ },
+ {
+ "epoch": 14.285714285714286,
+ "grad_norm": 1.4042483568191528,
+ "learning_rate": 5.810526315789474e-05,
+ "loss": 2.8584,
+ "step": 2500
+ },
+ {
+ "epoch": 17.142857142857142,
+ "grad_norm": 0.9517878890037537,
+ "learning_rate": 4.7578947368421054e-05,
+ "loss": 2.8587,
+ "step": 3000
+ },
+ {
+ "epoch": 17.142857142857142,
+ "eval_loss": 2.99222993850708,
+ "eval_runtime": 29.1002,
+ "eval_samples_per_second": 24.055,
+ "eval_steps_per_second": 3.024,
+ "eval_wer": 1.0,
+ "step": 3000
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 5250,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 30,
+ "save_steps": 500,
+ "stateful_callbacks": {
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": false
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 3.895420904615186e+18,
+ "train_batch_size": 8,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-3000/training_args.bin b/checkpoint-3000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7b42982e0ed3b4e8e4f9bda8f5b0897e3991a29b
--- /dev/null
+++ b/checkpoint-3000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17179d390d1d4b5d96939de5d843713fcef39c2ad6e18ec212571b6be7fd1cf
+size 5048
diff --git a/checkpoint-3000/vocab.json b/checkpoint-3000/vocab.json
new file mode 100644
index 0000000000000000000000000000000000000000..720cb7cedb3b1d6f9a9304535f5184757c21f649
--- /dev/null
+++ b/checkpoint-3000/vocab.json
@@ -0,0 +1,31 @@
+{
+ "[PAD]": 28,
+ "[UNK]": 27,
+ "a": 0,
+ "b": 2,
+ "c": 9,
+ "d": 8,
+ "e": 1,
+ "f": 4,
+ "g": 14,
+ "h": 16,
+ "i": 19,
+ "j": 11,
+ "k": 5,
+ "l": 7,
+ "m": 17,
+ "n": 25,
+ "o": 18,
+ "p": 22,
+ "q": 26,
+ "r": 23,
+ "s": 3,
+ "t": 15,
+ "u": 13,
+ "v": 6,
+ "w": 21,
+ "x": 12,
+ "y": 10,
+ "z": 20,
+ "|": 24
+}
diff --git a/checkpoint-3500/added_tokens.json b/checkpoint-3500/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..cc95e40ec61ca6dc6f02948ceaad78a75e854f3f
--- /dev/null
+++ b/checkpoint-3500/added_tokens.json
@@ -0,0 +1,4 @@
+{
+ "": 30,
+ "": 29
+}
diff --git a/checkpoint-3500/config.json b/checkpoint-3500/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ce6afb5abdb755f8a3c760398662bbeb930c6cef
--- /dev/null
+++ b/checkpoint-3500/config.json
@@ -0,0 +1,118 @@
+{
+ "_name_or_path": "facebook/wav2vec2-base",
+ "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": 0.1,
+ "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": 0.0,
+ "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": 28,
+ "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": "4.41.1",
+ "use_weighted_layer_sum": false,
+ "vocab_size": 32,
+ "xvector_output_dim": 512
+}
diff --git a/checkpoint-3500/model.safetensors b/checkpoint-3500/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fbdbe66a80625be2eb45338e0fb7eaa4f215b6fc
--- /dev/null
+++ b/checkpoint-3500/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b636a2a00705de0138c45a075ee49f6489d549b9fe202566c887306f3c0a985
+size 377611120
diff --git a/checkpoint-3500/optimizer.pt b/checkpoint-3500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..40055f9a1fe9b29568bc658f019056a58ea3778d
--- /dev/null
+++ b/checkpoint-3500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a39513d3b8b4714cc99620cc17b4bd80bd7b4530512b800054e8fd2292f0237
+size 755348794
diff --git a/checkpoint-3500/preprocessor_config.json b/checkpoint-3500/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c626b5517871d529f0ed94aded16d875d0dd4ea2
--- /dev/null
+++ b/checkpoint-3500/preprocessor_config.json
@@ -0,0 +1,10 @@
+{
+ "do_normalize": true,
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+ "feature_size": 1,
+ "padding_side": "right",
+ "padding_value": 0.0,
+ "processor_class": "Wav2Vec2Processor",
+ "return_attention_mask": false,
+ "sampling_rate": 16000
+}
diff --git a/checkpoint-3500/rng_state.pth b/checkpoint-3500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..17e0f521e7a6de359e66c0ecd631d4d6388fa306
--- /dev/null
+++ b/checkpoint-3500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9e575475bfcd3e70bda3ee27b6b421707d9231fb7f15399d4eb90c258afb3d
+size 14308
diff --git a/checkpoint-3500/scheduler.pt b/checkpoint-3500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..da11194181971149d89ebfc813d729cea62fb574
--- /dev/null
+++ b/checkpoint-3500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02995736038cfa25f80743d92c8376d0ee0a7847ccaffabc22cd5c173b080898
+size 1064
diff --git a/checkpoint-3500/special_tokens_map.json b/checkpoint-3500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..7f1669a2a2a16dae6adcf40b222f836ed75cbd1e
--- /dev/null
+++ b/checkpoint-3500/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "[PAD]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "[UNK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ }
+}
diff --git a/checkpoint-3500/tokenizer_config.json b/checkpoint-3500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa10530c450758d82ee7c9c929838cf2ba1ac18e
--- /dev/null
+++ b/checkpoint-3500/tokenizer_config.json
@@ -0,0 +1,48 @@
+{
+ "added_tokens_decoder": {
+ "27": {
+ "content": "[UNK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "28": {
+ "content": "[PAD]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "29": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "30": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "",
+ "clean_up_tokenization_spaces": true,
+ "do_lower_case": false,
+ "eos_token": "",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "[PAD]",
+ "processor_class": "Wav2Vec2Processor",
+ "replace_word_delimiter_char": " ",
+ "target_lang": null,
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
+ "unk_token": "[UNK]",
+ "word_delimiter_token": "|"
+}
diff --git a/checkpoint-3500/trainer_state.json b/checkpoint-3500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..550c9d43e74fa1fd3802c4ac939eb75947e9d97e
--- /dev/null
+++ b/checkpoint-3500/trainer_state.json
@@ -0,0 +1,109 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 20.0,
+ "eval_steps": 1000,
+ "global_step": 3500,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 2.857142857142857,
+ "grad_norm": 0.991371750831604,
+ "learning_rate": 9.8e-05,
+ "loss": 3.541,
+ "step": 500
+ },
+ {
+ "epoch": 5.714285714285714,
+ "grad_norm": 0.3066103756427765,
+ "learning_rate": 8.96842105263158e-05,
+ "loss": 2.8609,
+ "step": 1000
+ },
+ {
+ "epoch": 5.714285714285714,
+ "eval_loss": 3.1199309825897217,
+ "eval_runtime": 29.6116,
+ "eval_samples_per_second": 23.639,
+ "eval_steps_per_second": 2.972,
+ "eval_wer": 1.0,
+ "step": 1000
+ },
+ {
+ "epoch": 8.571428571428571,
+ "grad_norm": 0.7332219481468201,
+ "learning_rate": 7.915789473684211e-05,
+ "loss": 2.8625,
+ "step": 1500
+ },
+ {
+ "epoch": 11.428571428571429,
+ "grad_norm": 0.29804107546806335,
+ "learning_rate": 6.863157894736843e-05,
+ "loss": 2.8589,
+ "step": 2000
+ },
+ {
+ "epoch": 11.428571428571429,
+ "eval_loss": 3.051466941833496,
+ "eval_runtime": 29.5006,
+ "eval_samples_per_second": 23.728,
+ "eval_steps_per_second": 2.983,
+ "eval_wer": 1.0,
+ "step": 2000
+ },
+ {
+ "epoch": 14.285714285714286,
+ "grad_norm": 1.4042483568191528,
+ "learning_rate": 5.810526315789474e-05,
+ "loss": 2.8584,
+ "step": 2500
+ },
+ {
+ "epoch": 17.142857142857142,
+ "grad_norm": 0.9517878890037537,
+ "learning_rate": 4.7578947368421054e-05,
+ "loss": 2.8587,
+ "step": 3000
+ },
+ {
+ "epoch": 17.142857142857142,
+ "eval_loss": 2.99222993850708,
+ "eval_runtime": 29.1002,
+ "eval_samples_per_second": 24.055,
+ "eval_steps_per_second": 3.024,
+ "eval_wer": 1.0,
+ "step": 3000
+ },
+ {
+ "epoch": 20.0,
+ "grad_norm": 1.560330867767334,
+ "learning_rate": 3.7052631578947375e-05,
+ "loss": 2.8581,
+ "step": 3500
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 5250,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 30,
+ "save_steps": 500,
+ "stateful_callbacks": {
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": false
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 4.5374223294573235e+18,
+ "train_batch_size": 8,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-3500/training_args.bin b/checkpoint-3500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7b42982e0ed3b4e8e4f9bda8f5b0897e3991a29b
--- /dev/null
+++ b/checkpoint-3500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17179d390d1d4b5d96939de5d843713fcef39c2ad6e18ec212571b6be7fd1cf
+size 5048
diff --git a/checkpoint-3500/vocab.json b/checkpoint-3500/vocab.json
new file mode 100644
index 0000000000000000000000000000000000000000..720cb7cedb3b1d6f9a9304535f5184757c21f649
--- /dev/null
+++ b/checkpoint-3500/vocab.json
@@ -0,0 +1,31 @@
+{
+ "[PAD]": 28,
+ "[UNK]": 27,
+ "a": 0,
+ "b": 2,
+ "c": 9,
+ "d": 8,
+ "e": 1,
+ "f": 4,
+ "g": 14,
+ "h": 16,
+ "i": 19,
+ "j": 11,
+ "k": 5,
+ "l": 7,
+ "m": 17,
+ "n": 25,
+ "o": 18,
+ "p": 22,
+ "q": 26,
+ "r": 23,
+ "s": 3,
+ "t": 15,
+ "u": 13,
+ "v": 6,
+ "w": 21,
+ "x": 12,
+ "y": 10,
+ "z": 20,
+ "|": 24
+}
diff --git a/checkpoint-4000/added_tokens.json b/checkpoint-4000/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..cc95e40ec61ca6dc6f02948ceaad78a75e854f3f
--- /dev/null
+++ b/checkpoint-4000/added_tokens.json
@@ -0,0 +1,4 @@
+{
+ "": 30,
+ "": 29
+}
diff --git a/checkpoint-4000/config.json b/checkpoint-4000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ce6afb5abdb755f8a3c760398662bbeb930c6cef
--- /dev/null
+++ b/checkpoint-4000/config.json
@@ -0,0 +1,118 @@
+{
+ "_name_or_path": "facebook/wav2vec2-base",
+ "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": 0.1,
+ "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": 0.0,
+ "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": 28,
+ "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": "4.41.1",
+ "use_weighted_layer_sum": false,
+ "vocab_size": 32,
+ "xvector_output_dim": 512
+}
diff --git a/checkpoint-4000/model.safetensors b/checkpoint-4000/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fe91d64a7d25239f730e5b757360250ba52aeca7
--- /dev/null
+++ b/checkpoint-4000/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e31a0571b00e2e106f57c2d89f9bfa2071529f941ba07b1c0d43d30fc1e6f9b
+size 377611120
diff --git a/checkpoint-4000/optimizer.pt b/checkpoint-4000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9ef7bfc8b97bde72aa7e990330ea179659ab9617
--- /dev/null
+++ b/checkpoint-4000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ff86da5e675a3e049910b59212e1b781f6c7a29ecf8af7630658dae6dabaf0
+size 755348794
diff --git a/checkpoint-4000/preprocessor_config.json b/checkpoint-4000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c626b5517871d529f0ed94aded16d875d0dd4ea2
--- /dev/null
+++ b/checkpoint-4000/preprocessor_config.json
@@ -0,0 +1,10 @@
+{
+ "do_normalize": true,
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+ "feature_size": 1,
+ "padding_side": "right",
+ "padding_value": 0.0,
+ "processor_class": "Wav2Vec2Processor",
+ "return_attention_mask": false,
+ "sampling_rate": 16000
+}
diff --git a/checkpoint-4000/rng_state.pth b/checkpoint-4000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..72b60424c2b81cf096c6a86486e3f33a3b59825d
--- /dev/null
+++ b/checkpoint-4000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3166ef885c5cd11436318692cfb6445383e1aee770da912b41a66a114f8fcee3
+size 14308
diff --git a/checkpoint-4000/scheduler.pt b/checkpoint-4000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..797f9a5256f8dbd295202f5e1e14cf039e7bc41f
--- /dev/null
+++ b/checkpoint-4000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f0db999c1f2b233c421b54d04dab160ff4dbe060c33128f45c6518834cabe6
+size 1064
diff --git a/checkpoint-4000/special_tokens_map.json b/checkpoint-4000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..7f1669a2a2a16dae6adcf40b222f836ed75cbd1e
--- /dev/null
+++ b/checkpoint-4000/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "[PAD]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "[UNK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ }
+}
diff --git a/checkpoint-4000/tokenizer_config.json b/checkpoint-4000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa10530c450758d82ee7c9c929838cf2ba1ac18e
--- /dev/null
+++ b/checkpoint-4000/tokenizer_config.json
@@ -0,0 +1,48 @@
+{
+ "added_tokens_decoder": {
+ "27": {
+ "content": "[UNK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "28": {
+ "content": "[PAD]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "29": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "30": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "",
+ "clean_up_tokenization_spaces": true,
+ "do_lower_case": false,
+ "eos_token": "",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "[PAD]",
+ "processor_class": "Wav2Vec2Processor",
+ "replace_word_delimiter_char": " ",
+ "target_lang": null,
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
+ "unk_token": "[UNK]",
+ "word_delimiter_token": "|"
+}
diff --git a/checkpoint-4000/trainer_state.json b/checkpoint-4000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..a16064d511afd8f542d0aac2e69ed667563a9c7c
--- /dev/null
+++ b/checkpoint-4000/trainer_state.json
@@ -0,0 +1,125 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 22.857142857142858,
+ "eval_steps": 1000,
+ "global_step": 4000,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 2.857142857142857,
+ "grad_norm": 0.991371750831604,
+ "learning_rate": 9.8e-05,
+ "loss": 3.541,
+ "step": 500
+ },
+ {
+ "epoch": 5.714285714285714,
+ "grad_norm": 0.3066103756427765,
+ "learning_rate": 8.96842105263158e-05,
+ "loss": 2.8609,
+ "step": 1000
+ },
+ {
+ "epoch": 5.714285714285714,
+ "eval_loss": 3.1199309825897217,
+ "eval_runtime": 29.6116,
+ "eval_samples_per_second": 23.639,
+ "eval_steps_per_second": 2.972,
+ "eval_wer": 1.0,
+ "step": 1000
+ },
+ {
+ "epoch": 8.571428571428571,
+ "grad_norm": 0.7332219481468201,
+ "learning_rate": 7.915789473684211e-05,
+ "loss": 2.8625,
+ "step": 1500
+ },
+ {
+ "epoch": 11.428571428571429,
+ "grad_norm": 0.29804107546806335,
+ "learning_rate": 6.863157894736843e-05,
+ "loss": 2.8589,
+ "step": 2000
+ },
+ {
+ "epoch": 11.428571428571429,
+ "eval_loss": 3.051466941833496,
+ "eval_runtime": 29.5006,
+ "eval_samples_per_second": 23.728,
+ "eval_steps_per_second": 2.983,
+ "eval_wer": 1.0,
+ "step": 2000
+ },
+ {
+ "epoch": 14.285714285714286,
+ "grad_norm": 1.4042483568191528,
+ "learning_rate": 5.810526315789474e-05,
+ "loss": 2.8584,
+ "step": 2500
+ },
+ {
+ "epoch": 17.142857142857142,
+ "grad_norm": 0.9517878890037537,
+ "learning_rate": 4.7578947368421054e-05,
+ "loss": 2.8587,
+ "step": 3000
+ },
+ {
+ "epoch": 17.142857142857142,
+ "eval_loss": 2.99222993850708,
+ "eval_runtime": 29.1002,
+ "eval_samples_per_second": 24.055,
+ "eval_steps_per_second": 3.024,
+ "eval_wer": 1.0,
+ "step": 3000
+ },
+ {
+ "epoch": 20.0,
+ "grad_norm": 1.560330867767334,
+ "learning_rate": 3.7052631578947375e-05,
+ "loss": 2.8581,
+ "step": 3500
+ },
+ {
+ "epoch": 22.857142857142858,
+ "grad_norm": 0.43670666217803955,
+ "learning_rate": 2.652631578947369e-05,
+ "loss": 2.856,
+ "step": 4000
+ },
+ {
+ "epoch": 22.857142857142858,
+ "eval_loss": 3.0176596641540527,
+ "eval_runtime": 30.2333,
+ "eval_samples_per_second": 23.153,
+ "eval_steps_per_second": 2.911,
+ "eval_wer": 1.0,
+ "step": 4000
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 5250,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 30,
+ "save_steps": 500,
+ "stateful_callbacks": {
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": false
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 5.192300868316301e+18,
+ "train_batch_size": 8,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-4000/training_args.bin b/checkpoint-4000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7b42982e0ed3b4e8e4f9bda8f5b0897e3991a29b
--- /dev/null
+++ b/checkpoint-4000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17179d390d1d4b5d96939de5d843713fcef39c2ad6e18ec212571b6be7fd1cf
+size 5048
diff --git a/checkpoint-4000/vocab.json b/checkpoint-4000/vocab.json
new file mode 100644
index 0000000000000000000000000000000000000000..720cb7cedb3b1d6f9a9304535f5184757c21f649
--- /dev/null
+++ b/checkpoint-4000/vocab.json
@@ -0,0 +1,31 @@
+{
+ "[PAD]": 28,
+ "[UNK]": 27,
+ "a": 0,
+ "b": 2,
+ "c": 9,
+ "d": 8,
+ "e": 1,
+ "f": 4,
+ "g": 14,
+ "h": 16,
+ "i": 19,
+ "j": 11,
+ "k": 5,
+ "l": 7,
+ "m": 17,
+ "n": 25,
+ "o": 18,
+ "p": 22,
+ "q": 26,
+ "r": 23,
+ "s": 3,
+ "t": 15,
+ "u": 13,
+ "v": 6,
+ "w": 21,
+ "x": 12,
+ "y": 10,
+ "z": 20,
+ "|": 24
+}
diff --git a/checkpoint-4500/added_tokens.json b/checkpoint-4500/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..cc95e40ec61ca6dc6f02948ceaad78a75e854f3f
--- /dev/null
+++ b/checkpoint-4500/added_tokens.json
@@ -0,0 +1,4 @@
+{
+ "": 30,
+ "": 29
+}
diff --git a/checkpoint-4500/config.json b/checkpoint-4500/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ce6afb5abdb755f8a3c760398662bbeb930c6cef
--- /dev/null
+++ b/checkpoint-4500/config.json
@@ -0,0 +1,118 @@
+{
+ "_name_or_path": "facebook/wav2vec2-base",
+ "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": 0.1,
+ "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": 0.0,
+ "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": 28,
+ "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": "4.41.1",
+ "use_weighted_layer_sum": false,
+ "vocab_size": 32,
+ "xvector_output_dim": 512
+}
diff --git a/checkpoint-4500/model.safetensors b/checkpoint-4500/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a99e68260c57e3fbb96b3c42010807280ac1f6af
--- /dev/null
+++ b/checkpoint-4500/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac7574a6db8eade496f8281543ec513e1f42adfb87048e58fc90f5d0fcc4efc
+size 377611120
diff --git a/checkpoint-4500/optimizer.pt b/checkpoint-4500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ebd03936ec310e71f91f702f17e34d7494267b19
--- /dev/null
+++ b/checkpoint-4500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2be17cffff3ec12710b8d447c759fd8bca1508415e593aed3597c954b62a0ce
+size 755348794
diff --git a/checkpoint-4500/preprocessor_config.json b/checkpoint-4500/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c626b5517871d529f0ed94aded16d875d0dd4ea2
--- /dev/null
+++ b/checkpoint-4500/preprocessor_config.json
@@ -0,0 +1,10 @@
+{
+ "do_normalize": true,
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+ "feature_size": 1,
+ "padding_side": "right",
+ "padding_value": 0.0,
+ "processor_class": "Wav2Vec2Processor",
+ "return_attention_mask": false,
+ "sampling_rate": 16000
+}
diff --git a/checkpoint-4500/rng_state.pth b/checkpoint-4500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fab636ff214ec3a7c675fe654cba6f65b44c9ac1
--- /dev/null
+++ b/checkpoint-4500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9f4346ae9d81f950d14851002e0f180df4cdbd30f07b619c9dba2119c8f4fb
+size 14244
diff --git a/checkpoint-4500/scheduler.pt b/checkpoint-4500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..77c60835722ee08dde89f372e831433ec60dc479
--- /dev/null
+++ b/checkpoint-4500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0149f57fc12864b688e1f2f8232baf86c1d67599df5810e19f880a1e9e37f825
+size 1064
diff --git a/checkpoint-4500/special_tokens_map.json b/checkpoint-4500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..7f1669a2a2a16dae6adcf40b222f836ed75cbd1e
--- /dev/null
+++ b/checkpoint-4500/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "[PAD]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "[UNK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ }
+}
diff --git a/checkpoint-4500/tokenizer_config.json b/checkpoint-4500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa10530c450758d82ee7c9c929838cf2ba1ac18e
--- /dev/null
+++ b/checkpoint-4500/tokenizer_config.json
@@ -0,0 +1,48 @@
+{
+ "added_tokens_decoder": {
+ "27": {
+ "content": "[UNK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "28": {
+ "content": "[PAD]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "29": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "30": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "",
+ "clean_up_tokenization_spaces": true,
+ "do_lower_case": false,
+ "eos_token": "",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "[PAD]",
+ "processor_class": "Wav2Vec2Processor",
+ "replace_word_delimiter_char": " ",
+ "target_lang": null,
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
+ "unk_token": "[UNK]",
+ "word_delimiter_token": "|"
+}
diff --git a/checkpoint-4500/trainer_state.json b/checkpoint-4500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..a259450f8d53ddd3e37e202d16fecd2dc4cf7c08
--- /dev/null
+++ b/checkpoint-4500/trainer_state.json
@@ -0,0 +1,132 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 25.714285714285715,
+ "eval_steps": 1000,
+ "global_step": 4500,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 2.857142857142857,
+ "grad_norm": 0.991371750831604,
+ "learning_rate": 9.8e-05,
+ "loss": 3.541,
+ "step": 500
+ },
+ {
+ "epoch": 5.714285714285714,
+ "grad_norm": 0.3066103756427765,
+ "learning_rate": 8.96842105263158e-05,
+ "loss": 2.8609,
+ "step": 1000
+ },
+ {
+ "epoch": 5.714285714285714,
+ "eval_loss": 3.1199309825897217,
+ "eval_runtime": 29.6116,
+ "eval_samples_per_second": 23.639,
+ "eval_steps_per_second": 2.972,
+ "eval_wer": 1.0,
+ "step": 1000
+ },
+ {
+ "epoch": 8.571428571428571,
+ "grad_norm": 0.7332219481468201,
+ "learning_rate": 7.915789473684211e-05,
+ "loss": 2.8625,
+ "step": 1500
+ },
+ {
+ "epoch": 11.428571428571429,
+ "grad_norm": 0.29804107546806335,
+ "learning_rate": 6.863157894736843e-05,
+ "loss": 2.8589,
+ "step": 2000
+ },
+ {
+ "epoch": 11.428571428571429,
+ "eval_loss": 3.051466941833496,
+ "eval_runtime": 29.5006,
+ "eval_samples_per_second": 23.728,
+ "eval_steps_per_second": 2.983,
+ "eval_wer": 1.0,
+ "step": 2000
+ },
+ {
+ "epoch": 14.285714285714286,
+ "grad_norm": 1.4042483568191528,
+ "learning_rate": 5.810526315789474e-05,
+ "loss": 2.8584,
+ "step": 2500
+ },
+ {
+ "epoch": 17.142857142857142,
+ "grad_norm": 0.9517878890037537,
+ "learning_rate": 4.7578947368421054e-05,
+ "loss": 2.8587,
+ "step": 3000
+ },
+ {
+ "epoch": 17.142857142857142,
+ "eval_loss": 2.99222993850708,
+ "eval_runtime": 29.1002,
+ "eval_samples_per_second": 24.055,
+ "eval_steps_per_second": 3.024,
+ "eval_wer": 1.0,
+ "step": 3000
+ },
+ {
+ "epoch": 20.0,
+ "grad_norm": 1.560330867767334,
+ "learning_rate": 3.7052631578947375e-05,
+ "loss": 2.8581,
+ "step": 3500
+ },
+ {
+ "epoch": 22.857142857142858,
+ "grad_norm": 0.43670666217803955,
+ "learning_rate": 2.652631578947369e-05,
+ "loss": 2.856,
+ "step": 4000
+ },
+ {
+ "epoch": 22.857142857142858,
+ "eval_loss": 3.0176596641540527,
+ "eval_runtime": 30.2333,
+ "eval_samples_per_second": 23.153,
+ "eval_steps_per_second": 2.911,
+ "eval_wer": 1.0,
+ "step": 4000
+ },
+ {
+ "epoch": 25.714285714285715,
+ "grad_norm": 1.1510722637176514,
+ "learning_rate": 1.6000000000000003e-05,
+ "loss": 2.8548,
+ "step": 4500
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 5250,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 30,
+ "save_steps": 500,
+ "stateful_callbacks": {
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": false
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 5.835659411682157e+18,
+ "train_batch_size": 8,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-4500/training_args.bin b/checkpoint-4500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7b42982e0ed3b4e8e4f9bda8f5b0897e3991a29b
--- /dev/null
+++ b/checkpoint-4500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17179d390d1d4b5d96939de5d843713fcef39c2ad6e18ec212571b6be7fd1cf
+size 5048
diff --git a/checkpoint-4500/vocab.json b/checkpoint-4500/vocab.json
new file mode 100644
index 0000000000000000000000000000000000000000..720cb7cedb3b1d6f9a9304535f5184757c21f649
--- /dev/null
+++ b/checkpoint-4500/vocab.json
@@ -0,0 +1,31 @@
+{
+ "[PAD]": 28,
+ "[UNK]": 27,
+ "a": 0,
+ "b": 2,
+ "c": 9,
+ "d": 8,
+ "e": 1,
+ "f": 4,
+ "g": 14,
+ "h": 16,
+ "i": 19,
+ "j": 11,
+ "k": 5,
+ "l": 7,
+ "m": 17,
+ "n": 25,
+ "o": 18,
+ "p": 22,
+ "q": 26,
+ "r": 23,
+ "s": 3,
+ "t": 15,
+ "u": 13,
+ "v": 6,
+ "w": 21,
+ "x": 12,
+ "y": 10,
+ "z": 20,
+ "|": 24
+}
diff --git a/checkpoint-5000/added_tokens.json b/checkpoint-5000/added_tokens.json
new file mode 100644
index 0000000000000000000000000000000000000000..cc95e40ec61ca6dc6f02948ceaad78a75e854f3f
--- /dev/null
+++ b/checkpoint-5000/added_tokens.json
@@ -0,0 +1,4 @@
+{
+ "": 30,
+ "": 29
+}
diff --git a/checkpoint-5000/config.json b/checkpoint-5000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ce6afb5abdb755f8a3c760398662bbeb930c6cef
--- /dev/null
+++ b/checkpoint-5000/config.json
@@ -0,0 +1,118 @@
+{
+ "_name_or_path": "facebook/wav2vec2-base",
+ "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": 0.1,
+ "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": 0.0,
+ "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": 28,
+ "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": "4.41.1",
+ "use_weighted_layer_sum": false,
+ "vocab_size": 32,
+ "xvector_output_dim": 512
+}
diff --git a/checkpoint-5000/model.safetensors b/checkpoint-5000/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e1f09ee74d65a77de6a24390cbae98ec4ed8f861
--- /dev/null
+++ b/checkpoint-5000/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31684d3625dd5b0086e782f441e26a0693cd5d9d4c59aa346b49c7ed428f2094
+size 377611120
diff --git a/checkpoint-5000/optimizer.pt b/checkpoint-5000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..98f7314fa3ebae342807ce44b959c00768772c64
--- /dev/null
+++ b/checkpoint-5000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b82fd8fcbc2efc2fbaeadde4e799be322b0ed0ea67701c2ed5e3135bfea7d70
+size 755348794
diff --git a/checkpoint-5000/preprocessor_config.json b/checkpoint-5000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c626b5517871d529f0ed94aded16d875d0dd4ea2
--- /dev/null
+++ b/checkpoint-5000/preprocessor_config.json
@@ -0,0 +1,10 @@
+{
+ "do_normalize": true,
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+ "feature_size": 1,
+ "padding_side": "right",
+ "padding_value": 0.0,
+ "processor_class": "Wav2Vec2Processor",
+ "return_attention_mask": false,
+ "sampling_rate": 16000
+}
diff --git a/checkpoint-5000/rng_state.pth b/checkpoint-5000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..64ff640a1aa73a9fa26a3b94ca69ec5e3ecceab7
--- /dev/null
+++ b/checkpoint-5000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f53c5f870c1cbc34bcd2ea2b92fdccdd12bb2c2d59788b7fc2a29208755354
+size 14308
diff --git a/checkpoint-5000/scheduler.pt b/checkpoint-5000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f69e49e7925b0685951db906b1d930c325a24447
--- /dev/null
+++ b/checkpoint-5000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e07307f04d2f64629121585383d319599a1faffe9f428eb841383c23244cd8
+size 1064
diff --git a/checkpoint-5000/special_tokens_map.json b/checkpoint-5000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..7f1669a2a2a16dae6adcf40b222f836ed75cbd1e
--- /dev/null
+++ b/checkpoint-5000/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "[PAD]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "[UNK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ }
+}
diff --git a/checkpoint-5000/tokenizer_config.json b/checkpoint-5000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa10530c450758d82ee7c9c929838cf2ba1ac18e
--- /dev/null
+++ b/checkpoint-5000/tokenizer_config.json
@@ -0,0 +1,48 @@
+{
+ "added_tokens_decoder": {
+ "27": {
+ "content": "[UNK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "28": {
+ "content": "[PAD]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "29": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "30": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "",
+ "clean_up_tokenization_spaces": true,
+ "do_lower_case": false,
+ "eos_token": "",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "[PAD]",
+ "processor_class": "Wav2Vec2Processor",
+ "replace_word_delimiter_char": " ",
+ "target_lang": null,
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
+ "unk_token": "[UNK]",
+ "word_delimiter_token": "|"
+}
diff --git a/checkpoint-5000/trainer_state.json b/checkpoint-5000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..56f082b7e58770290add5f5d5b38877456654405
--- /dev/null
+++ b/checkpoint-5000/trainer_state.json
@@ -0,0 +1,148 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 28.571428571428573,
+ "eval_steps": 1000,
+ "global_step": 5000,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 2.857142857142857,
+ "grad_norm": 0.991371750831604,
+ "learning_rate": 9.8e-05,
+ "loss": 3.541,
+ "step": 500
+ },
+ {
+ "epoch": 5.714285714285714,
+ "grad_norm": 0.3066103756427765,
+ "learning_rate": 8.96842105263158e-05,
+ "loss": 2.8609,
+ "step": 1000
+ },
+ {
+ "epoch": 5.714285714285714,
+ "eval_loss": 3.1199309825897217,
+ "eval_runtime": 29.6116,
+ "eval_samples_per_second": 23.639,
+ "eval_steps_per_second": 2.972,
+ "eval_wer": 1.0,
+ "step": 1000
+ },
+ {
+ "epoch": 8.571428571428571,
+ "grad_norm": 0.7332219481468201,
+ "learning_rate": 7.915789473684211e-05,
+ "loss": 2.8625,
+ "step": 1500
+ },
+ {
+ "epoch": 11.428571428571429,
+ "grad_norm": 0.29804107546806335,
+ "learning_rate": 6.863157894736843e-05,
+ "loss": 2.8589,
+ "step": 2000
+ },
+ {
+ "epoch": 11.428571428571429,
+ "eval_loss": 3.051466941833496,
+ "eval_runtime": 29.5006,
+ "eval_samples_per_second": 23.728,
+ "eval_steps_per_second": 2.983,
+ "eval_wer": 1.0,
+ "step": 2000
+ },
+ {
+ "epoch": 14.285714285714286,
+ "grad_norm": 1.4042483568191528,
+ "learning_rate": 5.810526315789474e-05,
+ "loss": 2.8584,
+ "step": 2500
+ },
+ {
+ "epoch": 17.142857142857142,
+ "grad_norm": 0.9517878890037537,
+ "learning_rate": 4.7578947368421054e-05,
+ "loss": 2.8587,
+ "step": 3000
+ },
+ {
+ "epoch": 17.142857142857142,
+ "eval_loss": 2.99222993850708,
+ "eval_runtime": 29.1002,
+ "eval_samples_per_second": 24.055,
+ "eval_steps_per_second": 3.024,
+ "eval_wer": 1.0,
+ "step": 3000
+ },
+ {
+ "epoch": 20.0,
+ "grad_norm": 1.560330867767334,
+ "learning_rate": 3.7052631578947375e-05,
+ "loss": 2.8581,
+ "step": 3500
+ },
+ {
+ "epoch": 22.857142857142858,
+ "grad_norm": 0.43670666217803955,
+ "learning_rate": 2.652631578947369e-05,
+ "loss": 2.856,
+ "step": 4000
+ },
+ {
+ "epoch": 22.857142857142858,
+ "eval_loss": 3.0176596641540527,
+ "eval_runtime": 30.2333,
+ "eval_samples_per_second": 23.153,
+ "eval_steps_per_second": 2.911,
+ "eval_wer": 1.0,
+ "step": 4000
+ },
+ {
+ "epoch": 25.714285714285715,
+ "grad_norm": 1.1510722637176514,
+ "learning_rate": 1.6000000000000003e-05,
+ "loss": 2.8548,
+ "step": 4500
+ },
+ {
+ "epoch": 28.571428571428573,
+ "grad_norm": 0.9515011310577393,
+ "learning_rate": 5.4736842105263165e-06,
+ "loss": 2.8531,
+ "step": 5000
+ },
+ {
+ "epoch": 28.571428571428573,
+ "eval_loss": 3.0313847064971924,
+ "eval_runtime": 29.8329,
+ "eval_samples_per_second": 23.464,
+ "eval_steps_per_second": 2.95,
+ "eval_wer": 1.0,
+ "step": 5000
+ }
+ ],
+ "logging_steps": 500,
+ "max_steps": 5250,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 30,
+ "save_steps": 500,
+ "stateful_callbacks": {
+ "TrainerControl": {
+ "args": {
+ "should_epoch_stop": false,
+ "should_evaluate": false,
+ "should_log": false,
+ "should_save": true,
+ "should_training_stop": false
+ },
+ "attributes": {}
+ }
+ },
+ "total_flos": 6.487789626604962e+18,
+ "train_batch_size": 8,
+ "trial_name": null,
+ "trial_params": null
+}
diff --git a/checkpoint-5000/training_args.bin b/checkpoint-5000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7b42982e0ed3b4e8e4f9bda8f5b0897e3991a29b
--- /dev/null
+++ b/checkpoint-5000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17179d390d1d4b5d96939de5d843713fcef39c2ad6e18ec212571b6be7fd1cf
+size 5048
diff --git a/checkpoint-5000/vocab.json b/checkpoint-5000/vocab.json
new file mode 100644
index 0000000000000000000000000000000000000000..720cb7cedb3b1d6f9a9304535f5184757c21f649
--- /dev/null
+++ b/checkpoint-5000/vocab.json
@@ -0,0 +1,31 @@
+{
+ "[PAD]": 28,
+ "[UNK]": 27,
+ "a": 0,
+ "b": 2,
+ "c": 9,
+ "d": 8,
+ "e": 1,
+ "f": 4,
+ "g": 14,
+ "h": 16,
+ "i": 19,
+ "j": 11,
+ "k": 5,
+ "l": 7,
+ "m": 17,
+ "n": 25,
+ "o": 18,
+ "p": 22,
+ "q": 26,
+ "r": 23,
+ "s": 3,
+ "t": 15,
+ "u": 13,
+ "v": 6,
+ "w": 21,
+ "x": 12,
+ "y": 10,
+ "z": 20,
+ "|": 24
+}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ce6afb5abdb755f8a3c760398662bbeb930c6cef
--- /dev/null
+++ b/config.json
@@ -0,0 +1,118 @@
+{
+ "_name_or_path": "facebook/wav2vec2-base",
+ "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": 0.1,
+ "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": 0.0,
+ "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": 28,
+ "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": "4.41.1",
+ "use_weighted_layer_sum": false,
+ "vocab_size": 32,
+ "xvector_output_dim": 512
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3c05e19078a8a794b3891c85098effa2626c55a5
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bcff76df4e4b831cc4ddd6c9cfaeae33815be2f5d37f998b56b201a69771f6a
+size 377611120
diff --git a/preprocessor_config.json b/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c626b5517871d529f0ed94aded16d875d0dd4ea2
--- /dev/null
+++ b/preprocessor_config.json
@@ -0,0 +1,10 @@
+{
+ "do_normalize": true,
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+ "feature_size": 1,
+ "padding_side": "right",
+ "padding_value": 0.0,
+ "processor_class": "Wav2Vec2Processor",
+ "return_attention_mask": false,
+ "sampling_rate": 16000
+}
diff --git a/runs/May26_03-52-15_instance-til-team-1/events.out.tfevents.1716695683.instance-til-team-1 b/runs/May26_03-52-15_instance-til-team-1/events.out.tfevents.1716695683.instance-til-team-1
new file mode 100644
index 0000000000000000000000000000000000000000..b45553f9daf84da365d2a5f667290897d93dd8c2
--- /dev/null
+++ b/runs/May26_03-52-15_instance-til-team-1/events.out.tfevents.1716695683.instance-til-team-1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:354955f04baa3d20f88642acc9c32b62c4722a4e912e33408a0e633ac7e7e6f4
+size 10499
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..7f1669a2a2a16dae6adcf40b222f836ed75cbd1e
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+ "bos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "[PAD]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "[UNK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ }
+}
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..fa10530c450758d82ee7c9c929838cf2ba1ac18e
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,48 @@
+{
+ "added_tokens_decoder": {
+ "27": {
+ "content": "[UNK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "28": {
+ "content": "[PAD]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false,
+ "special": false
+ },
+ "29": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "30": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "",
+ "clean_up_tokenization_spaces": true,
+ "do_lower_case": false,
+ "eos_token": "",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "[PAD]",
+ "processor_class": "Wav2Vec2Processor",
+ "replace_word_delimiter_char": " ",
+ "target_lang": null,
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
+ "unk_token": "[UNK]",
+ "word_delimiter_token": "|"
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7b42982e0ed3b4e8e4f9bda8f5b0897e3991a29b
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17179d390d1d4b5d96939de5d843713fcef39c2ad6e18ec212571b6be7fd1cf
+size 5048
diff --git a/vocab.json b/vocab.json
new file mode 100644
index 0000000000000000000000000000000000000000..720cb7cedb3b1d6f9a9304535f5184757c21f649
--- /dev/null
+++ b/vocab.json
@@ -0,0 +1,31 @@
+{
+ "[PAD]": 28,
+ "[UNK]": 27,
+ "a": 0,
+ "b": 2,
+ "c": 9,
+ "d": 8,
+ "e": 1,
+ "f": 4,
+ "g": 14,
+ "h": 16,
+ "i": 19,
+ "j": 11,
+ "k": 5,
+ "l": 7,
+ "m": 17,
+ "n": 25,
+ "o": 18,
+ "p": 22,
+ "q": 26,
+ "r": 23,
+ "s": 3,
+ "t": 15,
+ "u": 13,
+ "v": 6,
+ "w": 21,
+ "x": 12,
+ "y": 10,
+ "z": 20,
+ "|": 24
+}