meetrec/server/whisper-server/.dockerignore at 9d3e553833cf37d90f16b73b3ceca93f8fe0d2d2 - meetrec - Gitea: Git with a cup of tea

fegger/meetrec

Files

T

fegger ef59fc0fb4 Add dockerized whisper.cpp inference server (Vulkan GPU, Tailscale)

- server/whisper-server: compose stack built from the pinned whisper.cpp
  v1.9.3 release, same as the Android JNI layer
- Vulkan GPU backend (AMD Radeon AI PRO R9700 / RADV) with transparent
  CPU fallback and NO_GPU override; GGML models auto-download on first
  start (MODEL env, default large-v3)
- API bound to the Tailscale interface only (100.103.83.12:8080) since
  whisper-server has no authentication; render-group GID passthrough for
  /dev/dri
- validated locally: image builds, entrypoint downloads tiny, POST
  /inference returns verbose_json with language + segments; GPU-less
  fallback confirmed

2026-09-07 12:17:40 +02:00

7 lines

65 B

Plaintext

Raw Blame History

 models/
 *.bin
 *.part
 .git
 Dockerfile
 docker-compose.yml
 README.md