Whisper Small Hi - Sanchit Gandhi
This model is a fine-tuned version of openai/whisper-small on the AfriVoice dataset. It achieves the following results on the evaluation set:
- Loss: 1.0521
- Wer: 40.6692
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: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 40
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0308 | 16.1290 | 500 | 0.9322 | 41.8411 |
| 0.0011 | 32.2581 | 1000 | 1.0521 | 40.6692 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.1.0+cu118
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for KasuleTrevor/whisper-lingala-small-test-5
Base model
openai/whisper-smallDataset used to train KasuleTrevor/whisper-lingala-small-test-5
Evaluation results
- Wer on AfriVoiceself-reported40.669