Whisper Small Hi - Sanchit Gandhi
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4697
- Wer: 32.3415
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: 5000
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.092 | 2.4450 | 1000 | 0.2995 | 35.1562 |
0.023 | 4.8900 | 2000 | 0.3540 | 33.9330 |
0.0015 | 7.3350 | 3000 | 0.4215 | 32.3542 |
0.0004 | 9.7800 | 4000 | 0.4573 | 32.3246 |
0.0002 | 12.2249 | 5000 | 0.4697 | 32.3415 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- 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 shinsu/whisper-small-ft-001
Base model
openai/whisper-small