Downloads · 30 days
5
3% of all-time downloads
whisper-v3-arabic-cs
AmrShebl/whisper-v3-arabic-cs
whisper-v3-arabic-cs is a machine learning model from AmrShebl. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
183
Public
Repo size
5.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Feb 5, 2026
- Updated
- Feb 6, 2026
- SHA
- 86854d73
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-v3-arabic-cs
This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5133
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.6677 | 0.2910 | 200 | 0.7061 |
| 2.5546 | 0.5820 | 400 | 0.6191 |
| 2.2422 | 0.8730 | 600 | 0.5740 |
| 1.9604 | 1.1630 | 800 | 0.5558 |
| 1.7410 | 1.4540 | 1000 | 0.5445 |
| 1.8339 | 1.7450 | 1200 | 0.5246 |
| 1.1202 | 2.0349 | 1400 | 0.5161 |
| 1.1772 | 2.3259 | 1600 | 0.5168 |
| 1.2495 | 2.6170 | 1800 | 0.5141 |
| 1.2639 | 2.9080 | 2000 | 0.5133 |
Framework versions
- PEFT 0.18.1
- Transformers 5.0.0
- Pytorch 2.5.1+cu121
- Datasets 2.21.0
- Tokenizers 0.22.2
- Library
- peft
- License
- apache-2.0
- Created
- Feb 5, 2026
- Updated
- Feb 6, 2026