Instructions to use Supertone/supertonic-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Supertonic
How to use Supertone/supertonic-3 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
Support for Urdu & Pashto (Pakistani) languages
#16
by 8eacon - opened
Hi @8eacon ,
Thank you for the suggestion and for sharing the links.
Urdu (ur) and Pashto (ps) are not supported in the current Supertonic 3 release. We also do not currently provide a public training or fine-tuning pipeline for adding new languages yourself.
That said, the dataset/model references are helpful. We’ll review the resources you shared and consider Urdu and Pashto support for future updates if we can secure suitable data and validation coverage.
Thanks again for taking the time to share these.
juheon2 changed discussion status to closed
Thanks @juheon2
I found some more datasets here:
Pashto:
https://huggingface.co/datasets/Tensor-Labs/pashto-largest-corpus