Whisper medium 12
This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8225
- Cer: 29.3991
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 12000
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0214 | 12.05 | 2000 | 0.7735 | 57.5787 |
| 0.0107 | 24.1 | 4000 | 0.8499 | 41.2738 |
| 0.0013 | 36.14 | 6000 | 0.8238 | 31.5901 |
| 0.0023 | 48.19 | 8000 | 0.8371 | 30.6105 |
| 0.0 | 60.24 | 10000 | 0.8209 | 29.4550 |
| 0.0 | 72.29 | 12000 | 0.8225 | 29.3991 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 1