Whisper base Czech CV low LR
This model is a fine-tuned version of openai/whisper-base on the mozilla-foundation/common_voice_11_0 cs dataset. It achieves the following results on the evaluation set:
- Loss: 0.5171
- Wer: 42.9053
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-06
- train_batch_size: 64
- 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: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6046 | 4.01 | 1000 | 0.6535 | 52.3084 |
| 0.4037 | 8.02 | 2000 | 0.5706 | 46.6879 |
| 0.3172 | 12.03 | 3000 | 0.5369 | 44.1042 |
| 0.3606 | 16.04 | 4000 | 0.5218 | 43.0766 |
| 0.3792 | 21.01 | 5000 | 0.5171 | 42.9053 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2