whisper-base-en-emo-v1
This model is a fine-tuned version of openai/whisper-base on the Common Voice 17.0(Emotional Tag) dataset. It achieves the following results on the evaluation set:
- Loss: 0.9660
- Wer: 120.1005
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: 4
- eval_batch_size: 8
- seed: 42
- 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0074 | 40.0 | 1000 | 0.8128 | 130.1508 |
| 0.0002 | 80.0 | 2000 | 0.9065 | 114.5729 |
| 0.0001 | 120.0 | 3000 | 0.9507 | 109.0452 |
| 0.0001 | 160.0 | 4000 | 0.9660 | 120.1005 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 2
Model tree for iFaz/whisper-base-en-emo-v1
Base model
openai/whisper-baseDataset used to train iFaz/whisper-base-en-emo-v1
Evaluation results
- Wer on Common Voice 17.0(Emotional Tag)self-reported120.101