Instructions to use Supertone/supertonic-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Supertonic
How to use Supertone/supertonic-2 with Supertonic:
from supertonic import TTS tts = TTS(auto_download=True) style = tts.get_voice_style(voice_name="M1") text = "The train delay was announced at 4:45 PM on Wed, Apr 3, 2024 due to track maintenance." wav, duration = tts.synthesize(text, voice_style=style) tts.save_audio(wav, "output.wav")
- Notebooks
- Google Colab
- Kaggle
Mixing language misses words
#1
by datwelk - opened
Prompt:
Mais c'est vraiment "very good".
Output:
"Very good".
Not always reproducible, e.g. sometimes only "vraiment" misses. Using 5 step inference in the online demo (webgpu).
Hello! The current model appears to suffer from occasional skip/repeat issues. We're aware of this and are working to fix it. We hope to release an improved model as soon as possible!
Awesome! Issue is happening in every language tested. But so far! Super job you are doing!