RVC-Project / RVC-Project/Retrieval-based-Voice-Conversion-WebUI

IndexError: index -1 is out of bounds for axis 0 with size 0

Open
#689 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

following up
Dominant language
Python
Stars
38.4k
Forks
5.3k
PR merge metrics
No merged PRs in 30d

Description

I've been trying to set this up for a little while now, and have not managed to do it.
I got a trained model from a friend, (which works in the live-gui mode, and also performs excellent on his computer).

From what i have gathered is the AttributeError: 'NoneType' object has no attribute 'dtype' error, just there because it doesn't get the data it needs, so that's not the troublemaker.

I can't explain the error before it though:

Traceback (most recent call last):
  File "D:\RVC-beta-v2-0618\infer-web.py", line 201, in vc_single
    audio_opt = vc.pipeline(
  File "D:\RVC-beta-v2-0618\vc_infer_pipeline.py", line 349, in pipeline
    self.vc(
  File "D:\RVC-beta-v2-0618\vc_infer_pipeline.py", line 204, in vc
    npy = np.sum(big_npy[ix] * np.expand_dims(weight, axis=2), axis=1)
IndexError: index -1 is out of bounds for axis 0 with size 0

I have tried all the steps outlined in other issue-threads, but nothing seems to work.
If I'm missing something blatantly obvious, please tell me.

Thanks in advance

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the traceback in vc_infer_pipeline.py around line 204 and inspect how the trained model and input data reach vc.pipeline from infer-web.py. Reproduce the reported IndexError with the supplied setup, then identify what empty input causes it and verify that the inference path completes without the error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.