search

open-mmlab / Amphion

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
https://openhlt.github.io/amphion/
MIT License
4.41k stars 373 forks source link

[Help]: while trainning transfomerSVC #164

Closed suted2 closed 4 months ago

suted2 commented 5 months ago

Problem Overview

(Briefly and clearly describe the issue you're facing and seeking help with.)

Hello, While I train transformerSVC, 

TypeError: WhisperExtractor.extract_content_features() takes 2 positional arguments but 3 were given

Steps Taken

(Detail your attempts to resolve the issue, including any relevant steps or processes.) I add

Expected Outcome

(A clear and concise description of what you expected to happen.)

Screenshots

(If applicable, add screenshots to help explain your problem.) image

Environment Information

Additional context

(Add any other context about the problem here.)

suted2 commented 5 months ago

Oh, It works when i copy and paste at colab cell, -> it works when i change args -> wavs , lens to wavs. but even i change content_extractor.py it still doesn't work when i use run.sh

image

RMSnow commented 5 months ago

Hi @suted2 , sorry for that! I have patched for it. Would you mind trying this branch of PR https://github.com/open-mmlab/Amphion/pull/165?

suted2 commented 5 months ago

Okay! thx!!!

RMSnow commented 4 months ago

Hi @suted2, if you have any further questions about transformerSVC, feel free to re-open this issue. We are glad to follow up!