87 lines
3.1 KiB
Markdown
87 lines
3.1 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
license: gpl-3.0
|
||
|
|
datasets:
|
||
|
|
- MohamedRashad/arabic-english-code-switching
|
||
|
|
language:
|
||
|
|
- ar
|
||
|
|
- en
|
||
|
|
metrics:
|
||
|
|
- wer
|
||
|
|
pipeline_tag: automatic-speech-recognition
|
||
|
|
---
|
||
|
|
|
||
|
|
# 👳 Arabic-Whisper-CodeSwitching-Edition
|
||
|
|
|
||
|
|
This model is a fine-tuned version of [Whisper Large v2 by OpenAI](https://huggingface.co/openai/whisper-large-v2), trained on an [Arabic-English-code-switching](https://huggingface.co/datasets/MohamedRashad/arabic-english-code-switching) dataset.
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
## 📝 Model Details
|
||
|
|
|
||
|
|
### Model Description
|
||
|
|
|
||
|
|
The Arabic-Whisper-CodeSwitching-Edition is designed to handle Arabic audio with embedded English words. This model enhances the original Whisper Large v2 by improving its performance on Arabic-English code-switching speech
|
||
|
|
|
||
|
|
- **Developed by:** العبد لله
|
||
|
|
- **Model type:** Speech Recognition
|
||
|
|
- **Language(s) (NLP):** Arabic, English (in the context of Arabic audio)
|
||
|
|
- **License:** GPL-3.0
|
||
|
|
|
||
|
|
### Model Sources [optional]
|
||
|
|
|
||
|
|
<!-- Provide the basic links for the model. -->
|
||
|
|
|
||
|
|
- **Repository for data collection:** https://github.com/MohamedAliRashad/youtube-audio-collector
|
||
|
|
- **Demo:** https://huggingface.co/spaces/MohamedRashad/Arabic-Whisper-CodeSwitching-Edition
|
||
|
|
|
||
|
|
## 👷 Uses
|
||
|
|
|
||
|
|
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||
|
|
|
||
|
|
### Direct Use
|
||
|
|
|
||
|
|
The model can be used directly for transcribing Arabic speech that includes English words. It is particularly useful in multilingual environments where code-switching is common.
|
||
|
|
|
||
|
|
### Out-of-Scope Use
|
||
|
|
|
||
|
|
The model may not perform well on monolingual speech in languages other than Arabic or English, or on speech with code-switching in languages other than Arabic and English.
|
||
|
|
|
||
|
|
## 😨 Bias, Risks, and Limitations
|
||
|
|
|
||
|
|
### Recommendations
|
||
|
|
|
||
|
|
Users (both direct and downstream) should be made aware of the risks, biases, and limitations of the model. More information needed for further recommendations.
|
||
|
|
|
||
|
|
## 🔍 How to Get Started with the Model
|
||
|
|
|
||
|
|
Use the code below to get started with the model.
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import WhisperForConditionalGeneration, WhisperProcessor
|
||
|
|
|
||
|
|
processor = WhisperProcessor.from_pretrained("MohamedRashad/Arabic-Whisper-CodeSwitching-Edition")
|
||
|
|
model = WhisperForConditionalGeneration.from_pretrained("MohamedRashad/Arabic-Whisper-CodeSwitching-Edition")
|
||
|
|
|
||
|
|
# Example usage
|
||
|
|
inputs = processor("path_to_audio_file.wav", return_tensors="pt")
|
||
|
|
generated_ids = model.generate(inputs["input_features"])
|
||
|
|
transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)
|
||
|
|
print(transcription)
|
||
|
|
```
|
||
|
|
|
||
|
|
## 👨🎓 Citation
|
||
|
|
|
||
|
|
### BibTeX:
|
||
|
|
```bibtex
|
||
|
|
@misc{rashad2024arabicwhisper,
|
||
|
|
title={Arabic-Whisper-CodeSwitching-Edition},
|
||
|
|
author={Mohamed Rashad},
|
||
|
|
year={2024},
|
||
|
|
url={https://huggingface.co/spaces/MohamedRashad/Arabic-Whisper-CodeSwitching-Edition},
|
||
|
|
}
|
||
|
|
```
|
||
|
|
|
||
|
|
### APA:
|
||
|
|
Rashad, M. (2024). Arabic-Whisper-CodeSwitching-Edition. Retrieved from https://huggingface.co/spaces/MohamedRashad/Arabic-Whisper-CodeSwitching-Edition
|