Whisper small vi - Ox
This model is a fine-tuned version of openai/whisper-small-v3 on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7400
- Wer: 27.7004
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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0242 | 5.7471 | 1000 | 0.6118 | 28.1719 |
| 0.0011 | 11.4943 | 2000 | 0.6969 | 27.7662 |
| 0.0003 | 17.2414 | 3000 | 0.7266 | 27.6346 |
| 0.0002 | 22.9885 | 4000 | 0.7400 | 27.7004 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1
- Datasets 3.0.2
- Tokenizers 0.20.1
- Downloads last month
- 40
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.