Whisper Small Ar - AxAI
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: 0.8021
- Wer: 116.1695
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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0331 | 4.15 | 1000 | 0.5950 | 130.9519 |
| 0.0031 | 8.3 | 2000 | 0.7200 | 114.9724 |
| 0.0006 | 12.45 | 3000 | 0.7821 | 116.3405 |
| 0.0006 | 16.6 | 4000 | 0.8021 | 116.1695 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 5
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 UsmanAXAI/whisper-small-ft-common-voice-11-ar
Base model
openai/whisper-small