Whisper Small Hi - Sanchit Gandhi
This model is a fine-tuned version of openai/whisper-base on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 2.6321
- Wer: 208.6544
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: 2
- training_steps: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.4506 | 0.0159 | 1 | 2.6321 | 208.6544 |
| 2.7038 | 0.0317 | 2 | 2.6321 | 208.6544 |
| 2.8656 | 0.0476 | 3 | 2.6321 | 208.6544 |
| 2.5412 | 0.0635 | 4 | 2.6321 | 208.6544 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 101
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for sknud/whisper-base-gl
Base model
openai/whisper-base