Whisper Large V2 Ja - Anh Phuong
This model is a fine-tuned version of openai/whisper-largev2-ja-v2 on the Google fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.2626
- Wer: 58.2472
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 |
|---|---|---|---|---|
| 0.004 | 6.25 | 1000 | 0.2030 | 61.0044 |
| 0.0022 | 12.5 | 2000 | 0.2081 | 60.6105 |
| 0.0002 | 18.75 | 3000 | 0.2401 | 58.7888 |
| 0.0001 | 25.0 | 4000 | 0.2531 | 58.6411 |
| 0.0001 | 31.25 | 5000 | 0.2598 | 58.2472 |
| 0.0001 | 37.5 | 6000 | 0.2626 | 58.2472 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 20
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.