whisper-small-coser
This model is a fine-tuned version of openai/whisper-small on coser-asr dataset. It achieves the following results on the evaluation set:
- Loss: 0.7951
- Wer: 108.2685
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 |
|---|---|---|---|---|
| 0.8783 | 0.3 | 1000 | 0.9044 | 96.7315 |
| 0.7787 | 0.59 | 2000 | 0.8388 | 102.7047 |
| 0.7897 | 0.89 | 3000 | 0.8049 | 107.5558 |
| 0.6478 | 1.19 | 4000 | 0.7951 | 108.2685 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 4
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 johnatanebonilla/whisper-small-coser
Base model
openai/whisper-small