Upload folder using huggingface_hub

README.md

@@ -0,0 +1,58 @@
+---
+base_model: en_xlsr_100p_run2
+tags:
+- automatic-speech-recognition
+- ./train_dataset.py
+- generated_from_trainer
+model-index:
+- name: en_xlsr_100p_run2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# en_xlsr_100p_run2
+
+This model is a fine-tuned version of [en_xlsr_100p_run2](https://huggingface.co/en_xlsr_100p_run2) on the ./TRAIN_DATASET.PY - NA dataset.
+
+## 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: 3.6254652680427316e-07
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 40
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 52,
+  "<s>": 51
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 40.0,
+    "train_loss": 0.06863045204288915,
+    "train_runtime": 104273.7009,
+    "train_samples": 690961,
+    "train_samples_per_second": 265.057,
+    "train_steps_per_second": 16.566
+}

checkpoint-1684217/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 52,
+  "<s>": 51
+}

checkpoint-1684217/config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "en_xlsr_100p_run2",
+  "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": 0.05,
+  "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": 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": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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": 50,
+  "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
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 53,
+  "xvector_output_dim": 512
+}

checkpoint-1684217/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:577ac577869e1624e6c6e5608904d03d55b05866e45868592cb10c0c78407c31
+size 1262024780

checkpoint-1684217/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5911effc80e5680bcaecdae2ce4c6422e5d2530e3f53b002bd973efd14100a71
+size 2490594358

checkpoint-1684217/preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

checkpoint-1684217/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:644d9bcc3d5ea88b7e05bbeccf7d8903996779e80446ecc0915dfc5b7ad202e2
+size 15088

checkpoint-1684217/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:327cb9dd8f3d9d6a89c72773b9e13a6c854f138d4cff7efc298e8563a406edd8
+size 15024

checkpoint-1684217/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da595faffbd89c1de8a880ce888baaec3bd57c10d28e6a400c85cf54e5c0d62a
+size 15024

checkpoint-1684217/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c10d4f61aed81a2070c4161fa5bdb66d2af44e38feeab142940a7438018a3b73
+size 15024

checkpoint-1684217/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f9f9580d594ef8fdc6fa58995c9f8991ad03668d1072b3bf5f40d255cd08b5
+size 1064

checkpoint-1684217/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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
+  }
+}

checkpoint-1684217/tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "added_tokens_decoder": {
+    "49": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "config": null,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_type": "wav2vec2",
+  "trust_remote_code": false,
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

checkpoint-1684217/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11dd82ea17dc842ee2d75d40f4d045c7fba7e7ba20f355c4c3ca8510f93a6000
+size 4600

checkpoint-1684217/vocab.json

@@ -0,0 +1,53 @@
+{
+  "\b": 0,
+  "\"": 2,
+  "[PAD]": 50,
+  "[UNK]": 49,
+  "\\": 3,
+  "a": 4,
+  "b": 5,
+  "c": 6,
+  "d": 7,
+  "e": 8,
+  "f": 9,
+  "g": 10,
+  "h": 11,
+  "i": 12,
+  "j": 13,
+  "k": 14,
+  "l": 15,
+  "m": 16,
+  "n": 17,
+  "o": 18,
+  "p": 19,
+  "q": 20,
+  "r": 21,
+  "s": 22,
+  "t": 23,
+  "u": 24,
+  "v": 25,
+  "w": 26,
+  "x": 27,
+  "y": 28,
+  "z": 29,
+  "|": 1,
+  "ç": 30,
+  "é": 31,
+  "ş": 32,
+  "υ": 33,
+  "а": 34,
+  "в": 35,
+  "г": 36,
+  "д": 37,
+  "е": 38,
+  "к": 39,
+  "л": 40,
+  "н": 41,
+  "с": 42,
+  "ф": 43,
+  "ч": 44,
+  "​": 45,
+  "’": 46,
+  "⁄": 47,
+  "�": 48
+}

checkpoint-1727400/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 52,
+  "<s>": 51
+}

checkpoint-1727400/config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "en_xlsr_100p_run2",
+  "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": 0.05,
+  "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": 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": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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": 50,
+  "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
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 53,
+  "xvector_output_dim": 512
+}

checkpoint-1727400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2897b023267b3b3e6e3351fcfb93a550c2780d297bba28210efd6bc1e63a0563
+size 1262024780

checkpoint-1727400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01bb584eb9329a6a14671924a87bc000b61320aecfc14b6419b3aa99d5ca975a
+size 2490594358

checkpoint-1727400/preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

checkpoint-1727400/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d03f8fee69565cd2396c8b4d6b319b360cc518634cafcb45e036f9736b4b20b
+size 15088

checkpoint-1727400/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f9f6e0a2d88b3ef8e159bcae623df2f7af61ebeefba705b0facce79fdf0b9ba
+size 15024

checkpoint-1727400/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80310a32b9723a05d388f40be06111a0ec8d86e5f96e8868584527353f477f7f
+size 15024

checkpoint-1727400/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cb394689eafabe4e04dffb0dc05d389621cbf28e18a55bf5175f2378ba7e379
+size 15088

checkpoint-1727400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bee8faefc37b8b5dca284689930d028f8d26d8f5966977fddaaf5d498b318f27
+size 1064

checkpoint-1727400/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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
+  }
+}

checkpoint-1727400/tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "added_tokens_decoder": {
+    "49": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "config": null,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_type": "wav2vec2",
+  "trust_remote_code": false,
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

checkpoint-1727400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11dd82ea17dc842ee2d75d40f4d045c7fba7e7ba20f355c4c3ca8510f93a6000
+size 4600

checkpoint-1727400/vocab.json

@@ -0,0 +1,53 @@
+{
+  "\b": 0,
+  "\"": 2,
+  "[PAD]": 50,
+  "[UNK]": 49,
+  "\\": 3,
+  "a": 4,
+  "b": 5,
+  "c": 6,
+  "d": 7,
+  "e": 8,
+  "f": 9,
+  "g": 10,
+  "h": 11,
+  "i": 12,
+  "j": 13,
+  "k": 14,
+  "l": 15,
+  "m": 16,
+  "n": 17,
+  "o": 18,
+  "p": 19,
+  "q": 20,
+  "r": 21,
+  "s": 22,
+  "t": 23,
+  "u": 24,
+  "v": 25,
+  "w": 26,
+  "x": 27,
+  "y": 28,
+  "z": 29,
+  "|": 1,
+  "ç": 30,
+  "é": 31,
+  "ş": 32,
+  "υ": 33,
+  "а": 34,
+  "в": 35,
+  "г": 36,
+  "д": 37,
+  "е": 38,
+  "к": 39,
+  "л": 40,
+  "н": 41,
+  "с": 42,
+  "ф": 43,
+  "ч": 44,
+  "​": 45,
+  "’": 46,
+  "⁄": 47,
+  "�": 48
+}

config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "en_xlsr_100p_run2",
+  "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": 0.05,
+  "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": 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": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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": 50,
+  "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
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 53,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2897b023267b3b3e6e3351fcfb93a550c2780d297bba28210efd6bc1e63a0563
+size 1262024780

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "added_tokens_decoder": {
+    "49": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "52": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "config": null,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "tokenizer_type": "wav2vec2",
+  "trust_remote_code": false,
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 40.0,
+    "train_loss": 0.06863045204288915,
+    "train_runtime": 104273.7009,
+    "train_samples": 690961,
+    "train_samples_per_second": 265.057,
+    "train_steps_per_second": 16.566
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11dd82ea17dc842ee2d75d40f4d045c7fba7e7ba20f355c4c3ca8510f93a6000
+size 4600

vocab.json

@@ -0,0 +1,53 @@
+{
+  "\b": 0,
+  "\"": 2,
+  "[PAD]": 50,
+  "[UNK]": 49,
+  "\\": 3,
+  "a": 4,
+  "b": 5,
+  "c": 6,
+  "d": 7,
+  "e": 8,
+  "f": 9,
+  "g": 10,
+  "h": 11,
+  "i": 12,
+  "j": 13,
+  "k": 14,
+  "l": 15,
+  "m": 16,
+  "n": 17,
+  "o": 18,
+  "p": 19,
+  "q": 20,
+  "r": 21,
+  "s": 22,
+  "t": 23,
+  "u": 24,
+  "v": 25,
+  "w": 26,
+  "x": 27,
+  "y": 28,
+  "z": 29,
+  "|": 1,
+  "ç": 30,
+  "é": 31,
+  "ş": 32,
+  "υ": 33,
+  "а": 34,
+  "в": 35,
+  "г": 36,
+  "д": 37,
+  "е": 38,
+  "к": 39,
+  "л": 40,
+  "н": 41,
+  "с": 42,
+  "ф": 43,
+  "ч": 44,
+  "​": 45,
+  "’": 46,
+  "⁄": 47,
+  "�": 48
+}