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: 0.6458
- Wer: 41.3148
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: 8
- 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 |
|---|---|---|---|---|
| 0.4912 | 0.29 | 1000 | 0.8084 | 56.0128 |
| 0.3949 | 0.57 | 2000 | 0.7061 | 51.6301 |
| 0.3512 | 0.86 | 3000 | 0.6605 | 48.2202 |
| 0.2319 | 1.14 | 4000 | 0.6458 | 41.3148 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.13.3
- Downloads last month
- 14
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support