Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Whisper small Taiwanese - LoRA
This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6546
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: 0.001
- 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_ratio: 0.1
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9384 | 1.0 | 1550 | 0.9004 |
| 0.7257 | 2.0 | 3100 | 0.7403 |
| 0.4672 | 3.0 | 4650 | 0.6729 |
| 0.3205 | 4.0 | 6200 | 0.6546 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 107
Unable to determine this model’s pipeline type. Check the
docs
.