Whisper Small Vie - VIVOS
This model is a fine-tuned version of openai/whisper-small on the VIVOS Vietnamese Speech to Text dataset. It achieves the following results on the evaluation set:
- Loss: 0.2750
- Wer: 14.5295
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: 4
- 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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1775 | 0.3503 | 1000 | 0.3448 | 18.3693 |
| 0.2924 | 0.7005 | 2000 | 0.3088 | 17.1921 |
| 0.1059 | 1.0508 | 3000 | 0.2896 | 15.4776 |
| 0.1182 | 1.4011 | 4000 | 0.2889 | 15.5408 |
| 0.1089 | 1.7513 | 5000 | 0.2750 | 14.5295 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.2.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 116
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.
Dataset used to train ThucPD/whisper-small-vie
Evaluation results
- Wer on VIVOS Vietnamese Speech to Textself-reported14.530