openai/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: 1.0432
- Wer: 32.9559
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: 500
- training_steps: 7000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2448 | 1.02 | 1000 | 0.8498 | 41.7538 |
| 0.0367 | 2.04 | 2000 | 0.8609 | 35.7724 |
| 0.0095 | 3.06 | 3000 | 0.9109 | 34.9303 |
| 0.0048 | 4.09 | 4000 | 0.9602 | 34.3496 |
| 0.0009 | 5.11 | 5000 | 1.0041 | 33.2172 |
| 0.0003 | 7.01 | 6000 | 1.0362 | 33.1010 |
| 0.0006 | 8.03 | 7000 | 1.0432 | 32.9559 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 9