Inference code

#1
by jpgallegoar - opened

Hello, could you provide inference code to upsample a given wav file? Thank you very much. If possible, separate upsample_vocal.py and upsample_instr.py

Multimodal Art Projection org

Sorry, this model is not designed for audio input.
Maybe you can find these repos helpful.

  1. https://github.com/haoheliu/versatile_audio_super_resolution
  2. https://github.com/slp-rl/aero

I understand it's not directly possible, but I imagine it's possible if you do input wav -> tokenizer -> upsampler -> decoder, or is it not?

Sign up or log in to comment