Downloads · 30 days
8
11% of all-time downloads
whisper-small-informal-arabic-noaugmentation
Talyiamira/whisper-small-informal-arabic-noaugmentation
whisper-small-informal-arabic-noaugmentation is a automatic speech recognition model from Talyiamira. 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
74
Public
Parameters
242M
5.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Apr 13, 2025
- Updated
- Apr 13, 2025
- SHA
- ee2944ef
Base models
Datasets
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 Informal Arabic (No augmentation)
This model is a fine-tuned version of openai/whisper-small on the Informal Arabic dataset. It achieves the following results on the evaluation set:
- Loss: 0.7355
- Wer: 35.7845
- Cer: 11.7237
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: Use OptimizerNames.ADAMW_TORCH 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: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.1852 | 13.1579 | 500 | 0.5350 | 38.3517 | 13.5387 |
| 0.0035 | 26.3158 | 1000 | 0.6154 | 36.2284 | 11.9937 |
| 0.0014 | 39.4737 | 1500 | 0.6649 | 35.4127 | 11.5945 |
| 0.0004 | 52.6316 | 2000 | 0.7032 | 35.4726 | 11.6321 |
| 0.0003 | 65.7895 | 2500 | 0.7355 | 35.7845 | 11.7237 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- ar
- Created
- Apr 13, 2025
- Updated
- Apr 13, 2025