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

Easily train a good VC model with voice data <= 10 mins!
MIT License
24.92k stars 3.65k forks source link

Incorrect Pronunciation of single word 'He' after Conversion #2278

Open canadDN opened 3 months ago

canadDN commented 3 months ago

Hello,

I encountered an issue with the RVC (1006NVIDIA) when converting a TTS-generated voice file. Specifically, the single word "He" is not pronounced correctly after conversion. Instead of the expected pronunciation, the output sounds more like "swee" or "sui."

Steps to Reproduce:

  1. I used a TTS engine to generate a voice file that includes the single word "He."
  2. I applied RVC to convert the voice file.
  3. The output consistently mispronounces "He" across different RVC models I tried.

What I've Tried:

Expected Result:

The RVC conversion should accurately pronounce "He" as it is in the original file.

Actual Result:

The word "He" is incorrectly converted to something like "swee" or "sui."

I have attached the original he.wav file for reference. Any help or suggestions to resolve this issue would be greatly appreciated. he.zip

Thank you!

marktellez commented 1 month ago

I just found this or a similar issue.

"Mark" by itself becomes "Nark" "mark mark mark" becomes "mark mark mark"

It only seems to do it on short rvc audios.