search

abus-aikorea / voice-pro

Comprehensive Gradio WebUI for audio processing, powered by Whisper engines (Whisper, Faster-Whisper, Whisper-Timestamped). Features Voice Changer, zero-shot Voice Cloning, YouTube downloading, vocal isolation, Text-to-Speech (Edge-TTS, F5-TTS), and multi-language translation. Perfect for content creators and developers.
MIT License
966 stars 98 forks source link

Support for pytorch version: 2.4.1+cu124 #1

Closed pandayummy closed 1 week ago

pandayummy commented 1 month ago

pytorch version: 2.4.1+cu124 expect an upgrade

abus-aikorea commented 1 month ago

Your suggestions are very good. We will give priority consideration to your suggestions. We are very concerned about supporting the latest libraries, but it is not easy due to legacy Python pacakges.

pandayummy commented 1 month ago

I'm using comfyui, and that requires cu124 https://github.com/comfyanonymous/ComfyUI

image

bramvera commented 1 month ago

I'm using comfyui, and that requires cu124 https://github.com/comfyanonymous/ComfyUI

image

it would be better if you installed ComfyUI or Abus on the separated env.

abus-aikorea commented 1 week ago

Voice-Pro works in the Python 3.10 & PyTorch 2.5.1+cu121 environment from v1.6.x.

Additionally, the versions of the main packages in use are as follows: openai-whisper==20240930 faster-whisper==1.0.3 whisper-timestamped==1.15.5 gradio==4.44.1 torch==2.5.1+cu121 torchvision==0.20.1+cu121 torchaudio==2.5.1+cu121