New Finetune for XTTS

Browse Source

Interface cleaned
Documentation improved & expanded
Dataset generation improved:
- Better VAD detection
- Better debugging/information
- Better editing/managing transcriptions
- Basic audio editing
- Re-transcription on detections of duplicate audio when splitting large files.
- Control over model precision fp16/fp32/mixed
- Migrate to openai-whisper (also saving 1.5GB on installation requirements for cublas)
Testing stage allows you to choose what minimum length audio
Model export exports all audio with text file descriptions of too long/too short
Misc other improvements too numerous to mention

...

This commit is contained in:

erew123 authored and GitHub committed 2024-11-15 00:21:40 +00:00

1 parent 9df1065be0

commit 1bd8f6aed9

2 files changed

+2818 -1070

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

finetune.py

+2818 -1070

File diff suppressed because it is too large. Load diff

training_metrics.png

BIN

Binary file not shown.

Side by Side After Width:  |  Height:  |  Size: 47 KiB