<!-- 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. -->
Wav2Vec2LargeXlsr53-Bangla
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4997
- Wer: 0.4970
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: 0.0004
- train_batch_size: 24
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 7.488 | 1.43 | 250 | 3.5201 | 1.0 |
| 2.6655 | 2.85 | 500 | 0.9790 | 0.9119 |
| 0.8826 | 4.28 | 750 | 0.6536 | 0.7847 |
| 0.6013 | 5.71 | 1000 | 0.5361 | 0.7130 |
| 0.4814 | 7.14 | 1250 | 0.5032 | 0.6053 |
| 0.3934 | 8.57 | 1500 | 0.4729 | 0.5827 |
| 0.3394 | 10.0 | 1750 | 0.4785 | 0.6033 |
| 0.2916 | 11.43 | 2000 | 0.4887 | 0.5429 |
| 0.2637 | 12.85 | 2250 | 0.4672 | 0.5287 |
| 0.2299 | 14.28 | 2500 | 0.5027 | 0.5227 |
| 0.2056 | 15.71 | 2750 | 0.5079 | 0.5073 |
| 0.1915 | 17.14 | 3000 | 0.5002 | 0.4987 |
| 0.1772 | 18.57 | 3250 | 0.4930 | 0.5002 |
| 0.1739 | 20.0 | 3500 | 0.4997 | 0.4970 |
Framework versions
- Transformers 4.24.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
