taco/microWakeWord-Trainer-Nvidia-Docker
1
0
Fork 0
mirror of https://github.com/TaterTotterson/microWakeWord-Trainer-Nvidia-Docker.git synced 2026-08-12 07:55:33 -06:00
Code Issues Packages Projects Releases Wiki Activity

Release NVIDIA WakeWord Trainer v18

Browse Source
This commit is contained in:
MasterPhooey
2026-07-26 09:07:22 -05:00
parent 2eee70cb34
commit 6ee228e8d3
8 changed files with 360 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
WHATS_NEW.md
View File

@@ -1,2 +1,3 @@
- Fixed the training-status endpoint crashing after a training log was created because its log-tail limits were missing.
- Restored bounded, incremental training-log updates so the UI can continue showing live progress without repeatedly reading the entire log.
- Added Parakeet ONNX as a second local Auto Training STT engine alongside Faster Whisper.
- Replaced manual model, device, and compute fields with a simple engine selector and managed language-aware models.
- Added CUDA-enabled ONNX Runtime with CPU fallback, runtime reporting, and model-cache cleanup when switching engines.