Upload 8 files

README.md

@@ -0,0 +1,93 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: torgo_xlsr_finetune-M05-2
+  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. -->
+
+# torgo_xlsr_finetune-M05-2
+
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5128
+- Wer: 1.1148
+
+## 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
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Wer    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 22.2047       | 0.86  | 500   | 3.3446          | 0.9930 |
+| 3.3679        | 1.72  | 1000  | 2.9591          | 0.9930 |
+| 2.8813        | 2.58  | 1500  | 2.7978          | 0.9930 |
+| 2.7207        | 3.44  | 2000  | 2.5604          | 0.9930 |
+| 2.3274        | 4.3   | 2500  | 2.0135          | 1.4468 |
+| 1.5821        | 5.16  | 3000  | 1.6148          | 1.5686 |
+| 1.1549        | 6.02  | 3500  | 1.3447          | 1.5014 |
+| 0.8908        | 6.88  | 4000  | 1.3315          | 1.4524 |
+| 0.7204        | 7.75  | 4500  | 1.3250          | 1.3894 |
+| 0.6209        | 8.61  | 5000  | 1.2566          | 1.3697 |
+| 0.5507        | 9.47  | 5500  | 1.2300          | 1.3221 |
+| 0.4622        | 10.33 | 6000  | 1.3826          | 1.3165 |
+| 0.4503        | 11.19 | 6500  | 1.2769          | 1.2717 |
+| 0.4026        | 12.05 | 7000  | 1.3531          | 1.2955 |
+| 0.3617        | 12.91 | 7500  | 1.2806          | 1.2521 |
+| 0.3239        | 13.77 | 8000  | 1.5507          | 1.2437 |
+| 0.3051        | 14.63 | 8500  | 1.6217          | 1.2563 |
+| 0.2983        | 15.49 | 9000  | 1.5210          | 1.2185 |
+| 0.2766        | 16.35 | 9500  | 1.4787          | 1.2143 |
+| 0.2642        | 17.21 | 10000 | 1.6284          | 1.2311 |
+| 0.2358        | 18.07 | 10500 | 1.3203          | 1.1891 |
+| 0.2303        | 18.93 | 11000 | 1.5233          | 1.2185 |
+| 0.2166        | 19.79 | 11500 | 1.5111          | 1.2129 |
+| 0.2162        | 20.65 | 12000 | 1.5128          | 1.1919 |
+| 0.1981        | 21.51 | 12500 | 1.4668          | 1.1877 |
+| 0.1736        | 22.38 | 13000 | 1.5041          | 1.1485 |
+| 0.1725        | 23.24 | 13500 | 1.5306          | 1.1639 |
+| 0.1632        | 24.1  | 14000 | 1.3756          | 1.1373 |
+| 0.1597        | 24.96 | 14500 | 1.5404          | 1.1345 |
+| 0.1571        | 25.82 | 15000 | 1.4863          | 1.1359 |
+| 0.1569        | 26.68 | 15500 | 1.4775          | 1.1401 |
+| 0.1431        | 27.54 | 16000 | 1.5410          | 1.1218 |
+| 0.1373        | 28.4  | 16500 | 1.5212          | 1.1246 |
+| 0.1461        | 29.26 | 17000 | 1.5128          | 1.1148 |
+
+
+### Framework versions
+
+- Transformers 4.26.1
+- Pytorch 1.13.1+cu116
+- Datasets 1.18.3
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,116 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "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": 29,
+  "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": "4.26.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb49fa034ccbb8b33d43682404fb8f4f573f2fe80a15da69c8a4a4467a1ad115
+size 1262033069

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 +1,11 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "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 sha256:325e93df1672566cb2ae4e8a1e8a9e1eb4748e96533545b24012c830ed9d90cb
+size 3515

vocab.json

@@ -0,0 +1,32 @@
+{
+  "'": 13,
+  "[PAD]": 29,
+  "[UNK]": 28,
+  "a": 18,
+  "b": 20,
+  "c": 24,
+  "d": 25,
+  "e": 11,
+  "f": 7,
+  "g": 3,
+  "h": 17,
+  "i": 0,
+  "j": 23,
+  "k": 12,
+  "l": 22,
+  "m": 27,
+  "n": 19,
+  "o": 9,
+  "p": 21,
+  "q": 4,
+  "r": 1,
+  "s": 2,
+  "t": 10,
+  "u": 5,
+  "v": 8,
+  "w": 14,
+  "x": 26,
+  "y": 6,
+  "z": 15,
+  "|": 16
+}