Whisper Small Hre 4.5 - male and female voice - 4000 steps, metric CER, skip_special_tokens False
This model is a fine-tuned version of openai/whisper-small on the Hre audio dataset 4 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0065
- Cer Ortho: 0.0216
- Cer: 1.7857
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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer Ortho | Cer |
|---|---|---|---|---|---|
| 0.005 | 16.53 | 4000 | 0.0065 | 0.0216 | 1.7857 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for ntviet/whisper-small-hre4.5
Base model
openai/whisper-small