Whisper Small Hre 5.1 - male voice - 600 steps, metric CER
This model is a fine-tuned version of openai/whisper-small on the Hre audio dataset 5 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0374
- Cer Ortho: 14.9533
- Cer: 6.1224
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer Ortho | Cer |
|---|---|---|---|---|---|
| 0.0629 | 4.96 | 600 | 0.0374 | 14.9533 | 6.1224 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 73
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for ntviet/whisper-small-hre5.1-nam
Base model
openai/whisper-small