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: 0.5714
- Wer: 18.0638
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: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0067 | 9.78 | 1000 | 0.4138 | 18.9383 |
| 0.0008 | 19.56 | 2000 | 0.4948 | 18.4736 |
| 0.0001 | 29.34 | 3000 | 0.5353 | 18.0730 |
| 0.0001 | 39.12 | 4000 | 0.5624 | 18.0570 |
| 0.0 | 48.9 | 5000 | 0.5714 | 18.0638 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.18.1.dev0
- Tokenizers 0.15.2
- Downloads last month
- 4