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: 0.0005
- Cer: 89.7499
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: 16
- 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: 200
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0811 | 6.25 | 200 | 0.0445 | 107.9126 |
| 0.0036 | 12.5 | 400 | 0.0036 | 102.3726 |
| 0.0007 | 18.75 | 600 | 0.0007 | 83.6138 |
| 0.0005 | 25.0 | 800 | 0.0005 | 92.7887 |
| 0.0005 | 31.25 | 1000 | 0.0005 | 89.7499 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.1
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 8