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: 0.4278
- Wer: 33.0991
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: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0776 | 2.45 | 1000 | 0.3089 | 36.4514 |
| 0.0207 | 4.89 | 2000 | 0.3399 | 33.1372 |
| 0.0012 | 7.34 | 3000 | 0.4067 | 33.4081 |
| 0.0005 | 9.8 | 4000 | 0.4278 | 33.0991 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 118
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for lw2333/whisper-small-hi
Base model
openai/whisper-small