mirror of
https://github.com/TaterTotterson/microWakeWord-Trainer-Nvidia-Docker.git
synced 2026-08-12 07:55:33 -06:00
Release NVIDIA WakeWord Trainer v26
This commit is contained in:
@@ -1,2 +1 @@
|
||||
- Prevented unreadable audio files from freezing sample preparation by adding a bounded FFmpeg watchdog, safe cleanup, and visible normalization progress.
|
||||
- Kept primary and guided STT results visible after captures are automatically sorted into positive or negative training samples.
|
||||
- Restored MOSS-TTS-Nano generation with the current voice-cloning API so all four providers contribute to the final training corpus.
|
||||
|
||||
Reference in New Issue
Block a user