Whisper Small ar - majed test
This model is a fine-tuned version of uaepro/whisper-small-ar-2 on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3392
- Wer: 168.2218
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 |
---|---|---|---|---|
0.1459 | 0.41 | 1000 | 0.3714 | 182.4752 |
0.1378 | 0.82 | 2000 | 0.3486 | 177.9993 |
0.0738 | 1.24 | 3000 | 0.3513 | 184.2939 |
0.0855 | 1.65 | 4000 | 0.3392 | 168.2218 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 12
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.