luigisaetta/whisper-medium
This model is a fine-tuned version of openai/whisper-medium on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1531
- Wer: 5.5543
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
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 6000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2023 | 0.17 | 1000 | 0.1852 | 7.6354 |
| 0.1215 | 0.33 | 2000 | 0.1577 | 6.4088 |
| 0.0711 | 1.1 | 3000 | 0.1576 | 6.1324 |
| 0.0656 | 1.27 | 4000 | 0.1499 | 5.8786 |
| 0.0294 | 2.04 | 5000 | 0.1552 | 5.6234 |
| 0.0351 | 2.21 | 6000 | 0.1531 | 5.5543 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2