Whisper Small Hi - Sanchit Gandhi
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2779
- Wer: 31.8378
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.234 | 0.6116 | 1000 | 0.3321 | 39.7401 |
| 0.1173 | 1.2232 | 2000 | 0.2951 | 35.3086 |
| 0.1205 | 1.8349 | 3000 | 0.2779 | 33.7340 |
| 0.0506 | 2.4465 | 4000 | 0.2779 | 31.8378 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2