Whisper-Small-dadirri
This model is a fine-tuned version of openai/whisper-small on the hearing voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.0231
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: 100
- training_steps: 400
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
No log | 0.52 | 50 | 3.0035 |
4.521 | 1.03 | 100 | 1.4394 |
4.521 | 1.55 | 150 | 2.7847 |
1.8786 | 2.06 | 200 | 0.4913 |
1.8786 | 2.58 | 250 | 0.0458 |
0.0755 | 3.09 | 300 | 0.0379 |
0.0755 | 3.61 | 350 | 0.0285 |
0.0126 | 4.12 | 400 | 0.0231 |
Framework versions
- Transformers 4.38.0
- Pytorch 2.0.1+cu118
- Datasets 2.19.1
- Tokenizers 0.15.2
- Downloads last month
- 3