dmet/ai-voice-cloning
1
0
Fork 0
forked from mrq/ai-voice-cloning
Code Pull Requests Activity

fixed culling for validation based on audio duration not working

Browse Source
This commit is contained in:
mrq 2023-09-21 22:33:11 +00:00
parent 2fae5008fc
commit 17acfee5d0
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
modules/tortoise-tts

@ -1 +1 @@
Subproject commit b10c58436d6871c26485d30b203e6cfdd4167602
Subproject commit bf3b6c87aa825295f64a31d010fd5e896fbcda43

4
src/utils.py
View File

@ -2665,8 +2665,8 @@ def prepare_dataset( voice, use_segments=False, text_length=0, audio_length=0, p
culled = len(text) < text_length
#if not culled and audio_length > 0:
# culled = duration < audio_length
if not culled and audio_length > 0:
culled = duration < audio_length
line = f'audio/{file}|{phonemes if phonemize and phonemes else text}'