metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-small-ja
results: []
whisper-small-ja
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7645
- Wer: 23.2394
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: 8
- 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 | 1.43 | 10 | 1.2124 | 21.1268 |
| No log | 2.86 | 20 | 0.8283 | 884.5070 |
| 1.2688 | 4.29 | 30 | 0.7769 | 23.2394 |
| 1.2688 | 5.71 | 40 | 0.7645 | 23.2394 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cpu
- Datasets 2.8.0
- Tokenizers 0.13.2