voice-assistant-stack

T

bhetherman e845016b32 Pin tts-server Sopro model to a known-good HF revision

Loading from the unpinned main branch let an upstream repo restructure
(dropped vocoder_streaming.safetensors) crash-loop the tts container on
every boot for days; pin to the last snapshot with the full file set.

2026-09-27 02:02:43 -04:00

asr-server

Initial voice-assistant-stack: open-webui + spotify-voice-assistant submodules, asr/tts sidecars

2026-08-31 00:47:35 -04:00

mtp-relaxed-decoding

Add MTP_N_PARALLEL to entrypoint.sh, bump submodule pointers

2026-09-05 13:40:59 -04:00

open-webui @ 966140c3ef

Add MTP_N_PARALLEL to entrypoint.sh, bump submodule pointers

2026-09-05 13:40:59 -04:00

spotify-voice-assistant @ d1b27ab7b8

Bump spotify-voice-assistant submodule pointer

2026-09-05 14:47:36 -04:00

tts-server

Pin tts-server Sopro model to a known-good HF revision

2026-09-27 02:02:43 -04:00

.gitignore

Point submodules at bhetherman fork, ignore .venv, add requirements.txt

2026-08-31 01:04:36 -04:00

.gitmodules

Point submodules at bhetherman fork, ignore .venv, add requirements.txt

2026-08-31 01:04:36 -04:00

requirements.txt

Point submodules at bhetherman fork, ignore .venv, add requirements.txt

2026-08-31 01:04:36 -04:00