Whisper Small Hi - Sanchit Gandhi
This model is a fine-tuned version of nurzhanit/whisper-enhanced-ml on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0032
- Wer: 3.3254
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: 25
- training_steps: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7502 | 25.0 | 50 | 0.2821 | 4.5131 |
| 0.0435 | 50.0 | 100 | 0.0205 | 3.3254 |
| 0.0054 | 75.0 | 150 | 0.0041 | 3.3254 |
| 0.0038 | 100.0 | 200 | 0.0032 | 3.3254 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.2
- Tokenizers 0.19.1
- Downloads last month
- 424
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for nurzhanit/whisper-asphalt-v1
Unable to build the model tree, the base model loops to the model itself. Learn more.