BriereAssia/wav2vec2_finetuned_model

README.md

@@ -0,0 +1,91 @@
+---
+library_name: transformers
+license: mit
+base_model: facebook/w2v-bert-2.0
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_11_0
+metrics:
+- wer
+model-index:
+- name: w2v-V3
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_11_0
+      type: common_voice_11_0
+      config: ar
+      split: test
+      args: ar
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.16133249852681203
+---
+
+<!-- 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. -->
+
+# w2v-V3
+
+This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the common_voice_11_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1847
+- Wer: 0.1613
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- training_steps: 5000
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 1.566         | 0.0428 | 300  | 0.6246          | 0.5686 |
+| 0.462         | 0.0856 | 600  | 0.5791          | 0.3623 |
+| 0.4407        | 0.1284 | 900  | 0.4428          | 0.3232 |
+| 0.4036        | 0.1712 | 1200 | 0.4119          | 0.3066 |
+| 0.328         | 0.2139 | 1500 | 0.3693          | 0.2684 |
+| 0.3151        | 0.2567 | 1800 | 0.3102          | 0.2462 |
+| 0.2907        | 0.2995 | 2100 | 0.3221          | 0.2411 |
+| 0.2553        | 0.3423 | 2400 | 0.3061          | 0.2430 |
+| 0.2156        | 0.3851 | 2700 | 0.2857          | 0.2104 |
+| 0.2034        | 0.4279 | 3000 | 0.2516          | 0.2025 |
+| 0.2038        | 0.4707 | 3300 | 0.2395          | 0.1995 |
+| 0.1751        | 0.5135 | 3600 | 0.2372          | 0.1875 |
+| 0.1697        | 0.5563 | 3900 | 0.2063          | 0.1809 |
+| 0.1501        | 0.5991 | 4200 | 0.2005          | 0.1775 |
+| 0.1428        | 0.6418 | 4500 | 0.2024          | 0.1701 |
+| 0.1211        | 0.6846 | 4800 | 0.1883          | 0.1642 |
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.3.1
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "facebook/w2v-bert-2.0",
+  "activation_dropout": 0.0,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.1,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "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": 0.0,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 74,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "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": "4.49.0",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 77,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd465918ef2dbc33f95acc30c37b1bdc1102e8954b6c0ba83d2940de56157b82
+size 2423130260

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 1,
+  "processor_class": "Wav2Vec2BertProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce528dea8b5bf0e151afa7e137aa6a502cda237185baa550004044fcd28256bd
+size 5240