Whisper Small Ar - Abdallah Elbohy
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset For short transcription 30s but for long transcription it has some limitations and challenges. It achieves the following results on the evaluation set:
- Loss: 0.3791
- Wer: 49.8081
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 |
---|---|---|---|---|
0.0972 | 0.57 | 1000 | 0.3791 | 49.8081 |
0.0978 | 1.14 | 2000 | 0.3791 | 49.8081 |
0.0986 | 1.71 | 3000 | 0.3791 | 49.8081 |
0.1055 | 2.28 | 4000 | 0.3791 | 49.8081 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 11
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.