Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-model-small-ro-finetune-5k-25-25
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0817
- Wer: 0.3588
- Cer: 0.1600
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.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: 30
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 3.7445 | 1.0 | 94 | 1.5879 | 0.8776 | 0.7493 |
| 1.5931 | 2.0 | 188 | 1.1883 | 0.6682 | 0.7086 |
| 1.4058 | 3.0 | 282 | 1.1214 | 0.4901 | 0.3507 |
| 1.3409 | 4.0 | 376 | 1.0917 | 0.4718 | 0.2203 |
| 1.3097 | 5.0 | 470 | 1.0817 | 0.3588 | 0.1600 |
Framework versions
- PEFT 0.15.2
- Transformers 4.52.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for victors3136/whisper-model-small-ro-finetune-5k-25-25
Base model
openai/whisper-small