bhetherman
  • Joined on 2026-03-03
bhetherman pushed to main at bhetherman/open-webui 2026-09-27 02:02:58 -04:00
966140c3ef Give the MTP llama-server 4 parallel slots instead of 1
bhetherman pushed to main at bhetherman/spotify-voice-assistant 2026-09-27 02:02:57 -04:00
d1b27ab7b8 Restore correct room ID mapping, fix select_source race in wait guard
428579244a Revert room ID mapping swap -- original direction was correct
291f526a84 Disambiguate play_music vs queue_music by verb, not content type
2ed1ca1e99 Fix cold-start play_media failure and swap reversed room IDs
Compare 4 commits »
bhetherman pushed to main at bhetherman/voice-assistant-stack 2026-09-27 02:02:54 -04:00
e845016b32 Pin tts-server Sopro model to a known-good HF revision
2b05169b66 Bump spotify-voice-assistant submodule pointer
5e832c5496 Bump spotify-voice-assistant submodule pointer
96c8c547dd Bump spotify-voice-assistant submodule pointer
0ba2ea45be Add MTP_N_PARALLEL to entrypoint.sh, bump submodule pointers
Compare 5 commits »
bhetherman pushed to main at bhetherman/voice-assistant-stack 2026-09-04 11:33:32 -04:00
627904e130 Add relaxed-MTP llama-server build and wire it into the stack
bhetherman pushed to main at bhetherman/open-webui 2026-09-04 11:33:19 -04:00
6f583deff9 Add relaxed-MTP llama-server as a new connection, surface generation speed
bhetherman pushed to main at bhetherman/voice-assistant-stack 2026-08-31 01:06:18 -04:00
f0995c08ab Remove assistant-stack.code-workspace file
12ab57262e Point submodules at bhetherman fork, ignore .venv, add requirements.txt
Compare 2 commits »
bhetherman pushed to main at bhetherman/voice-assistant-stack 2026-08-31 00:47:38 -04:00
c2b92d96cb Initial voice-assistant-stack: open-webui + spotify-voice-assistant submodules, asr/tts sidecars
bhetherman created branch main in bhetherman/voice-assistant-stack 2026-08-31 00:47:38 -04:00
bhetherman pushed to main at bhetherman/spotify-voice-assistant 2026-08-31 00:46:55 -04:00
7249919006 Add tool-call disambiguation test harness for search_spotify/control_playback
bhetherman pushed to main at bhetherman/open-webui 2026-08-31 00:46:50 -04:00
7eff527d16 Add Authentik OIDC login, ollama-auth LAN proxy, and asr/tts sidecar wiring
bhetherman created repository bhetherman/voice-assistant-stack 2026-08-31 00:35:33 -04:00
bhetherman pushed to adding-video at bhetherman/live-voice-chat 2026-04-24 00:36:22 -04:00
44a10667c2 Enhance video handling and performance optimizations
bhetherman pushed to adding-video at bhetherman/live-voice-chat 2026-04-16 10:00:41 -04:00
129df7d1fa working ok
9debc56137 Add LightX2V + Wan2.2-TI2V-5B-Turbo GGUF experiment
56923ff424 test passing
fcf0be38bc t5 encoder fp8 seems to be working
2818b41004 first stab at adding video
Compare 5 commits »
bhetherman created branch adding-video in bhetherman/live-voice-chat 2026-04-16 10:00:41 -04:00
bhetherman pushed to main at bhetherman/MuseTalk 2026-04-14 23:04:57 -04:00
ca5b7a8f28 Make musetalk a proper Python package
bhetherman pushed to main at bhetherman/live-voice-chat 2026-04-08 11:43:30 -04:00
680c5b04cc Pre-download the spacy model that kokoro needs at runtime
d509f92a9d barge-in changes
175ed943df add KV-cache and move system promt to the config
c7c4019ecc add lm studio option
Compare 4 commits »
bhetherman pushed to main at bhetherman/live-voice-chat 2026-04-08 04:42:15 -04:00
08c5757b31 vad fix
bhetherman pushed to main at bhetherman/live-voice-chat 2026-04-08 04:08:46 -04:00
c07187aae1 add readme, remove torchvision
bhetherman pushed to main at bhetherman/live-voice-chat 2026-04-08 04:01:54 -04:00
263f39e0a3 Switch to CUDA 12.8 + ONNX-based VAD for RTX 5090 Blackwell support
bhetherman pushed to main at bhetherman/live-voice-chat 2026-04-08 03:05:36 -04:00
0305f1dccd updates for docker take 1