| license: cc-by-nc-4.0 | |
| license_link: https://huggingface.co/Tushe/shami-tts | |
| language: | |
| - ar | |
| base_model: | |
| - Tushe/shami-tts | |
| library_name: phoonnx | |
| pipeline_tag: text-to-speech | |
| tags: | |
| - onnx | |
| - tts | |
| - arabic | |
| - levantine | |
| - code-switching | |
| - vits | |
| - shami | |
| # OpenVoiceOS/phoonnx-shami | |
| ONNX export of [Tushe/shami-tts](https://huggingface.co/Tushe/shami-tts), | |
| a Levantine Arabic / English code-switching VITS model (HamsVITS), | |
| packaged for [phoonnx](https://github.com/TigreGotico/phoonnx). | |
| ## Files | |
| - `model.onnx` — exported HamsVITS ONNX graph | |
| - `config.json` — phoonnx voice configuration | |
| ## Usage | |
| ```python | |
| from phoonnx.model_manager import TTSModelManager | |
| manager = TTSModelManager() | |
| voice = manager.get_voice("Tushe/shami-tts") | |
| audio = voice.synthesize("مَرحَبا، this is a test.") | |
| ``` | |
| ## License | |
| CC BY-NC 4.0, same as the upstream [Tushe/shami-tts](https://huggingface.co/Tushe/shami-tts) model | |
| (non-commercial use only). This repository adds no license of its own. | |