Whisper small v5-en finetuned
This model is a fine-tuned version of openai/whisper-small on the my_audio_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.1560
- Wer: 5.6915
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 300
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1138 | 5.8309 | 1000 | 0.1326 | 6.3035 |
| 0.004 | 11.6618 | 2000 | 0.1507 | 5.7015 |
| 0.0014 | 17.4927 | 3000 | 0.1560 | 5.6915 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2
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.