whisper-small-collected-data
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: 0.6221
- Wer: 55.5283
- Cer: 44.5095
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: 500
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.0069 | 11.63 | 1000 | 0.5614 | 53.7696 | 42.3371 |
| 0.0011 | 23.26 | 2000 | 0.6221 | 55.5283 | 44.5095 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 7
Model tree for hoangdeeptry/whisper-small-collected-data
Base model
openai/whisper-small