Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
LaoASRModel
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8994
- Wer: 103.8716
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: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 900
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1146 | 0.1391 | 150 | 1.1055 | 100.3246 |
| 1.0660 | 0.2783 | 300 | 1.0561 | 101.1244 |
| 1.0197 | 0.4174 | 450 | 1.0082 | 101.7619 |
| 0.9737 | 0.5566 | 600 | 0.9590 | 102.0517 |
| 0.9257 | 0.6957 | 750 | 0.9164 | 102.6776 |
| 0.9122 | 0.8349 | 900 | 0.8994 | 103.8716 |
Framework versions
- PEFT 0.18.1
- Transformers 5.3.0
- Pytorch 2.9.0+cu126
- Datasets 4.8.3
- Tokenizers 0.22.2
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support