Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisereer-v0
This model is a fine-tuned version of openai/whisper-large-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8428
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch 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: 50
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4502 | 1.0 | 427 | 1.7092 |
| 1.2366 | 2.0 | 854 | 1.6973 |
| 1.1277 | 3.0 | 1281 | 1.6775 |
| 0.9028 | 4.0 | 1708 | 1.6519 |
| 0.7469 | 5.0 | 2135 | 1.7480 |
| 0.5263 | 5.9877 | 2556 | 1.8428 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.5.1+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for sudoping01/whisereer-v0
Base model
openai/whisper-large-v2