Stereo WAV files do not work

rsxdalv / tts-generation-webui

TTS Generation Web UI (Bark, MusicGen + AudioGen, Tortoise, RVC, Vocos, Demucs, SeamlessM4T, MAGNet, StyleTTS2, MMS, Stable Audio, Mars5, F5-TTS, ParlerTTS)

https://rsxdalv.github.io/tts-generation-webui/

MIT License

1.85k stars 202 forks source link

Stereo WAV files do not work #374

Closed Consequence6 closed 1 month ago

Consequence6 commented 2 months ago

When using a stereo audio file, with the Maha-TTS tab it returns RuntimeError: shape '[1, 1, 484463]' is invalid for input of size 968926

Converting the file to mono fixes it.

rsxdalv commented 1 month ago

Added a note about this in the UI, not something that I will fix now. The original project does not want to fix it in code.