Initial commit with copied content

README.md

@@ -0,0 +1,87 @@
+---
+base_model: facebook/wav2vec2-large
+license: apache-2.0
+metrics:
+- wer
+tags:
+- generated_from_trainer
+model-index:
+- name: wav2vec2-large-sw-cv-100hr-v2
+  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. -->
+
+# wav2vec2-large-sw-cv-100hr-v2
+
+This model is a fine-tuned version of [facebook/wav2vec2-large](https://huggingface.co/facebook/wav2vec2-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6293
+- Model Preparation Time: 0.004
+- Wer: 0.3558
+- Cer: 0.1353
+
+## 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: 0.0007
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.6
+- num_epochs: 120
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Model Preparation Time | Wer    | Cer    |
+|:-------------:|:-----:|:-----:|:---------------:|:----------------------:|:------:|:------:|
+| 3.5004        | 1.0   | 1040  | 0.7862          | 0.004                  | 0.6822 | 0.1909 |
+| 0.4704        | 2.0   | 2080  | 0.5245          | 0.004                  | 0.4970 | 0.1335 |
+| 0.3202        | 3.0   | 3120  | 0.4288          | 0.004                  | 0.3956 | 0.1066 |
+| 0.2551        | 4.0   | 4160  | 0.3800          | 0.004                  | 0.3644 | 0.0962 |
+| 0.2213        | 5.0   | 5200  | 0.3481          | 0.004                  | 0.3358 | 0.0911 |
+| 0.2005        | 6.0   | 6240  | 0.3241          | 0.004                  | 0.3101 | 0.0839 |
+| 0.1911        | 7.0   | 7280  | 0.3535          | 0.004                  | 0.3283 | 0.0924 |
+| 0.1854        | 8.0   | 8320  | 0.3161          | 0.004                  | 0.3002 | 0.0843 |
+| 0.1819        | 9.0   | 9360  | 0.3181          | 0.004                  | 0.3233 | 0.0964 |
+| 0.1788        | 10.0  | 10400 | 0.3099          | 0.004                  | 0.3086 | 0.0832 |
+| 0.1796        | 11.0  | 11440 | 0.3245          | 0.004                  | 0.3011 | 0.0827 |
+| 0.1805        | 12.0  | 12480 | 0.3068          | 0.004                  | 0.2967 | 0.0845 |
+| 0.1791        | 13.0  | 13520 | 0.3163          | 0.004                  | 0.3076 | 0.0864 |
+| 0.1812        | 14.0  | 14560 | 0.3336          | 0.004                  | 0.3104 | 0.0867 |
+| 0.1844        | 15.0  | 15600 | 0.3257          | 0.004                  | 0.3117 | 0.0864 |
+| 0.1884        | 16.0  | 16640 | 0.3440          | 0.004                  | 0.3136 | 0.0886 |
+| 0.1979        | 17.0  | 17680 | 0.3444          | 0.004                  | 0.3172 | 0.0899 |
+| 0.2058        | 18.0  | 18720 | 0.3286          | 0.004                  | 0.3456 | 0.1092 |
+| 0.2114        | 19.0  | 19760 | 0.3603          | 0.004                  | 0.3358 | 0.0969 |
+| 0.2229        | 20.0  | 20800 | 0.3658          | 0.004                  | 0.3301 | 0.0954 |
+| 0.2275        | 21.0  | 21840 | 0.3849          | 0.004                  | 0.3729 | 0.1197 |
+| 0.2351        | 22.0  | 22880 | 0.3753          | 0.004                  | 0.3488 | 0.1011 |
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.20.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 30,
+  "<s>": 29
+}

config.json

@@ -0,0 +1,110 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "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_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "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": 28,
+  "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": "4.44.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 31,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432f2259f912b888868671d767f53206439e33b1ddf0c8dc029579c4bd28e865
+size 1261893268

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": true,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

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": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "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",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:addc29842e1aea61589f273fb7374e928e102f4d16d48005bb202c4ed42df697
+size 5176

vocab.json

@@ -0,0 +1,31 @@
+{
+  "[PAD]": 28,
+  "[UNK]": 27,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "j": 10,
+  "k": 11,
+  "l": 12,
+  "m": 13,
+  "n": 14,
+  "o": 15,
+  "p": 16,
+  "q": 17,
+  "r": 18,
+  "s": 19,
+  "t": 20,
+  "u": 21,
+  "v": 22,
+  "w": 23,
+  "x": 24,
+  "y": 25,
+  "z": 26,
+  "|": 0
+}