Upload 8 files

README.md

@@ -0,0 +1,91 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: torgo_xlsr_finetune-M03-2
+  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-M03-2
+
+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: 0.2376
+- Wer: 0.5541
+
+## 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    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 23.6177       | 0.92  | 500   | 3.4289          | 1.0    |
+| 3.4209        | 1.85  | 1000  | 21.5765         | 1.0    |
+| 3.1586        | 2.77  | 1500  | 2.8397          | 1.0    |
+| 2.7993        | 3.69  | 2000  | 2.7192          | 1.2867 |
+| 2.644         | 4.61  | 2500  | 2.5331          | 1.2996 |
+| 2.4662        | 5.54  | 3000  | 2.1750          | 1.2341 |
+| 1.9879        | 6.46  | 3500  | 1.3732          | 1.2693 |
+| 1.4941        | 7.38  | 4000  | 0.8590          | 1.1900 |
+| 1.1848        | 8.3   | 4500  | 0.6774          | 1.1339 |
+| 0.9662        | 9.23  | 5000  | 0.5184          | 0.9856 |
+| 0.8094        | 10.15 | 5500  | 0.4515          | 0.9504 |
+| 0.6835        | 11.07 | 6000  | 0.3616          | 0.8457 |
+| 0.6111        | 11.99 | 6500  | 0.3209          | 0.8254 |
+| 0.5305        | 12.92 | 7000  | 0.3098          | 0.7902 |
+| 0.479         | 13.84 | 7500  | 0.2964          | 0.7569 |
+| 0.4369        | 14.76 | 8000  | 0.2447          | 0.7063 |
+| 0.3836        | 15.68 | 8500  | 0.2676          | 0.7063 |
+| 0.3628        | 16.61 | 9000  | 0.2714          | 0.7128 |
+| 0.3416        | 17.53 | 9500  | 0.2664          | 0.6766 |
+| 0.3297        | 18.45 | 10000 | 0.2510          | 0.6528 |
+| 0.2883        | 19.37 | 10500 | 0.2636          | 0.6493 |
+| 0.2694        | 20.3  | 11000 | 0.2556          | 0.6255 |
+| 0.2655        | 21.22 | 11500 | 0.2328          | 0.6186 |
+| 0.2364        | 22.14 | 12000 | 0.2293          | 0.6037 |
+| 0.241         | 23.06 | 12500 | 0.2587          | 0.5928 |
+| 0.2125        | 23.99 | 13000 | 0.2528          | 0.5843 |
+| 0.2101        | 24.91 | 13500 | 0.2315          | 0.5719 |
+| 0.1973        | 25.83 | 14000 | 0.2401          | 0.5769 |
+| 0.1914        | 26.75 | 14500 | 0.2380          | 0.5610 |
+| 0.1936        | 27.68 | 15000 | 0.2425          | 0.5551 |
+| 0.1808        | 28.6  | 15500 | 0.2425          | 0.5556 |
+| 0.1739        | 29.52 | 16000 | 0.2376          | 0.5541 |
+
+
+### 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 sha256:104a7447406efde142072e51b13a40f6af8f48b09cf3b83772249e073ec16ab0
+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 sha256:10016667ca4ca21d318178f1ec6b59103625efcb8d14f1b208456d988e57d43a
+size 3515

vocab.json

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