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: 0.0010
- Wer: 22.3549
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: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.3416 | 10.0 | 50 | 0.7715 | 69.5819 |
| 0.1814 | 20.0 | 100 | 0.0861 | 33.4898 |
| 0.0174 | 30.0 | 150 | 0.0096 | 22.3549 |
| 0.0038 | 40.0 | 200 | 0.0029 | 22.3549 |
| 0.0022 | 50.0 | 250 | 0.0019 | 22.3549 |
| 0.0016 | 60.0 | 300 | 0.0015 | 22.3549 |
| 0.0013 | 70.0 | 350 | 0.0012 | 22.3549 |
| 0.0012 | 80.0 | 400 | 0.0011 | 22.3549 |
| 0.0011 | 90.0 | 450 | 0.0010 | 22.3549 |
| 0.001 | 100.0 | 500 | 0.0010 | 22.3549 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.2
- Tokenizers 0.19.1
- Downloads last month
- 23,437
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 nurzhanit/whisper-enhanced-ml
Unable to build the model tree, the base model loops to the model itself. Learn more.