whisper-small-akan
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1860
- Wer: 48.9551
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: 0.0001
- train_batch_size: 32
- 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: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1893 | 10.0 | 250 | 0.8613 | 62.1906 |
| 0.0452 | 20.0 | 500 | 0.9964 | 55.3579 |
| 0.0211 | 30.0 | 750 | 1.0689 | 52.0824 |
| 0.0069 | 40.0 | 1000 | 1.1229 | 52.2306 |
| 0.0008 | 50.0 | 1250 | 1.1646 | 49.0885 |
| 0.0002 | 60.0 | 1500 | 1.1773 | 49.2663 |
| 0.0002 | 70.0 | 1750 | 1.1838 | 49.0885 |
| 0.0002 | 80.0 | 2000 | 1.1860 | 48.9551 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Inference API (serverless) is not available, repository is disabled.
Model tree for devkyle/whisper-small-dp-v4
Base model
openai/whisper-small
Finetuned
this model