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

Use higher sample rate for inference

Open
#2,092 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

I'm having issues with pronunciation and I believe that this is due to the input audio being downsampled to 16khz.
For example, I have an audio in 48khz that has clear pronunciation of some words, but when I downsample it to 16khz, it's hard to understand some words and I think the inference model has the same problem.

I think the solution would be to use a higher sample rate for inference.

So it this possible to use input audio with a higher sample rate?

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

The issue names no files, tests, or entry points; begin by locating where input audio is downsampled to 16 kHz and where inference accepts its sample rate. Determine whether higher-rate input is supported and validate pronunciation quality against the reported 48 kHz versus 16 kHz example.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
audio-video-rtc, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.