whisper-small-til-asr
This model is a fine-tuned version of openai/whisper-small.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0014
- Wer: 0.0665
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: 1.25e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0015 | 0.2540 | 200 | 0.0053 | 0.1994 |
| 0.0001 | 0.5079 | 400 | 0.0024 | 0.0831 |
| 0.0001 | 0.7619 | 600 | 0.0013 | 0.0831 |
| 0.0001 | 1.0159 | 800 | 0.0015 | 0.0665 |
| 0.0 | 1.2698 | 1000 | 0.0014 | 0.0665 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1