Whisper Small Vi - Anh Phuong
This model is a fine-tuned version of openai/whisper-small-vi-v2 on the vi 500 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1002
- Wer: 5.8290
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: 4
- 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 |
|---|---|---|---|---|
| 0.1638 | 0.2 | 1000 | 0.1707 | 9.6824 |
| 0.1233 | 0.4 | 2000 | 0.1302 | 7.4792 |
| 0.1063 | 0.6 | 3000 | 0.1097 | 6.4330 |
| 0.0962 | 0.8 | 4000 | 0.1002 | 5.8290 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- 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.