Whisper Small Ja - Haruto Kimura
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.9052
- Wer: 4750.0
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: 5
- training_steps: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 10.0 | 10 | 1.3778 | 370.0 |
| No log | 20.0 | 20 | 0.9597 | 1800.0 |
| 1.2408 | 30.0 | 30 | 0.9199 | 2020.0 |
| 1.2408 | 40.0 | 40 | 0.9052 | 4750.0 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 2
Model tree for kimupachipachi/whisper-medium-ja
Base model
openai/whisper-smallEvaluation results
- Wer on Common Voice 11.0test set self-reported4750.000