openai/whisper-medium
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7427
- Wer: 19.3902
- Cer: 8.7285
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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 | Cer |
|---|---|---|---|---|---|
| 0.0471 | 1.05 | 1000 | 0.5961 | 20.2895 | 8.9820 |
| 0.0194 | 2.11 | 2000 | 1.0999 | 22.6146 | 9.7105 |
| 0.002 | 4.02 | 3000 | 0.7289 | 20.2018 | 8.8379 |
| 0.0006 | 5.07 | 4000 | 0.7791 | 19.3683 | 8.4376 |
| 0.0003 | 6.13 | 5000 | 0.7427 | 19.3902 | 8.7285 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.