| license: mit | |
| language: | |
| - en | |
| pipeline_tag: text-to-speech | |
| tags: | |
| - MeloTTS | |
| - TTS | |
| ## Uses | |
| This model is trained using the [MeloTTS libary](https://github.com/myshell-ai/MeloTTS). To make it simpler to use, have I modified the original code and removed any unnecessary code. This code can be found in my [GitHub repository](https://github.com/dron3flyv3r/MeloTTS.git). | |
| ## Interface | |
| start by cloning the repository and installing the requirements: | |
| ```bash | |
| git clone https://github.com/dron3flyv3r/MeloTTS.git | |
| pip install -r requirements.txt | |
| ``` | |
| You can how use the model by running: | |
| ```python | |
| from melo.api import TTS | |
| model = TTS("GLADOS") | |
| def tts_file(text: str, path: str): | |
| model.tts_to_file(text, 0, path) | |
| def tts(text: str): | |
| temp_path = "temp.wav" | |
| tts_file(text, temp_path) | |
| tts("Hello, and again, welcome to the Aperture Science computer-aided enrichment center.") | |
| ``` | |
| ## Acknowledgements | |
| This model was trained using the [MeloTTS libary](https://github.com/myshell-ai/MeloTTS) by [myshell-ai](https://github.com/myshell-ai/MeloTTS). |