Downloads · 30 days
76
40% of all-time downloads
whisper-small-egyptian-arabic-3
WafaaFraih/whisper-small-egyptian-arabic-3
whisper-small-egyptian-arabic-3 is a machine learning model from WafaaFraih. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
190
Public
Parameters
242M
14.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Aug 23, 2024
- Updated
- Aug 25, 2024
- SHA
- e0ace4b8
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 Egyptian Arabic
This model is a fine-tuned version of openai/whisper-small on the Darija STT Mix dataset. It achieves the following results on the evaluation set:
- Loss: 0.6617
- Wer Ortho: 52.9142
- Wer: 48.7048
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.6715 | 0.8203 | 500 | 0.7303 | 64.8593 | 60.5440 |
| 0.4268 | 1.6407 | 1000 | 0.6617 | 52.9142 | 48.7048 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Type
- whisper
- License
- apache-2.0
- Languages
- ar
- Created
- Aug 23, 2024
- Updated
- Aug 25, 2024