Whisper Small Vi - Anh Phuong
This model is a fine-tuned version of openai/whisper-small-vi-v2 on the Google fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.4633
- Wer: 14.4308
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: 6000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0133 | 4.7619 | 1000 | 0.3913 | 15.3383 |
| 0.0009 | 9.5238 | 2000 | 0.4180 | 14.3227 |
| 0.0006 | 14.2857 | 3000 | 0.4382 | 14.6162 |
| 0.0003 | 19.0476 | 4000 | 0.4496 | 14.4269 |
| 0.0002 | 23.8095 | 5000 | 0.4594 | 14.4578 |
| 0.0002 | 28.5714 | 6000 | 0.4633 | 14.4308 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 4
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.