Whisper base Czech CV
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: 0.5394
- Wer: 33.9957
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: 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 |
|---|---|---|---|---|
| 0.206 | 4.01 | 1000 | 0.4356 | 36.2443 |
| 0.0332 | 8.02 | 2000 | 0.4583 | 34.0509 |
| 0.0074 | 12.03 | 3000 | 0.5119 | 34.4395 |
| 0.005 | 16.04 | 4000 | 0.5394 | 33.9957 |
| 0.0045 | 21.01 | 5000 | 0.5461 | 34.1025 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2