Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
whisper-model-large
This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7886
- Wer: 49.4306
- Cer: 23.9791
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: 2
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- 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: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 34.2487 | 1.4935 | 100 | 1.0020 | 68.4852 | 42.0288 |
| 33.6328 | 2.9869 | 200 | 0.9819 | 61.3877 | 35.4614 |
| 32.4449 | 4.4785 | 300 | 0.9390 | 54.4359 | 28.3477 |
| 30.1355 | 5.9720 | 400 | 0.8774 | 51.4036 | 25.6444 |
| 27.1357 | 7.4636 | 500 | 0.8188 | 49.6425 | 24.0758 |
| 25.8065 | 8.9570 | 600 | 0.7886 | 49.4306 | 23.9791 |
Framework versions
- PEFT 0.20.0
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2
- Downloads last month
- 65
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for danial1245/whisper-model-large
Base model
openai/whisper-large-v3