whisper-small-clean_6
This model is a fine-tuned version of openai/whisper-small on the lyhourt/clean_6 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3565
- Wer: 28.9442
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: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.1583 | 0.2 | 200 | 1.1107 | 87.1886 |
0.0074 | 1.028 | 400 | 0.4016 | 37.2835 |
0.1778 | 1.228 | 600 | 0.3914 | 34.0214 |
0.0027 | 2.056 | 800 | 0.3441 | 28.5647 |
0.1441 | 2.2560 | 1000 | 0.3565 | 28.9442 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 7