Downloads · 30 days
18
15% of all-time downloads
whisper-levantine
Laith05/whisper-levantine
whisper-levantine is a automatic speech recognition model from Laith05. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
124
Public
Parameters
242M
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 83%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Mar 25, 2026
- Updated
- Sep 23, 2026
- SHA
- 244b70d6
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
Whisper Small - Levantine Fine-Tuned
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: 0.7380
- Wer: 0.4142
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: 4
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1981 | 5.0 | 250 | 0.5457 | 0.4142 |
| 0.0949 | 10.0 | 500 | 0.6591 | 0.4231 |
| 0.0203 | 15.0 | 750 | 0.7231 | 0.4195 |
| 0.0129 | 20.0 | 1000 | 0.7380 | 0.4142 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- ar
- Created
- Mar 25, 2026
- Updated
- Sep 23, 2026