Hugging Face's logo

tenyaiida
/
FateApo_Datasets

voice
Model card Files
xet
Community
tenyaiida commited on
Commit
b268ab4
·
verified ·
1 Parent(s): 1b0e560

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -49,9 +49,7 @@ Update 2024/1/25: Both the first Siegfried model and "SiegfriedV2" have been rep
49
 
50
  Update 2024/1/4: A new voice "SiegfriedV2" has been added. Some notes below about the voice.
51
 
52
- While "SiegfriedV2" is a better quality and more accurate voice than "Siegfried", I have kept "Siegfried" in the file because in its testing, it sounds different than "SiegfriedV2". Notably it is a bit softer.
53
-
54
- General Model Notes: Both "Siegfried" and "SiegfriedV2" are very prone to voice cracking. I highly recommend lowering the "Protect voiceless consonants" factor to either 0.2 or 0.25 for best quality.
55
 
56
  Since it is a very low voice, it sounds strange with higher voices, and it may also have even more cracking in higher-pitched songs. Try lowering the pitch first, as it may already reduce the cracking.
57
 
 
49
 
50
  Update 2024/1/4: A new voice "SiegfriedV2" has been added. Some notes below about the voice.
51
 
52
+ The model is very prone to voice cracking. I highly recommend lowering the "Protect voiceless consonants" factor to either 0.2 or 0.25 for best quality.
 
 
53
 
54
  Since it is a very low voice, it sounds strange with higher voices, and it may also have even more cracking in higher-pitched songs. Try lowering the pitch first, as it may already reduce the cracking.
55