vh
f2792183d4
For brokkr's dataset foundry (operator-approved 2026-09-26, relayed). - stacks/lfm-vl-seat: llama.cpp server-cuda b11176 (digest-pinned), Q5_K_M + mmproj Q8_0, :8030; gateway alias lfm25-vl-3b (LiteLLM restarted, 36 s). Positive control exact; null control shows it describes a missing image. - stacks/vibevoice-asr-seat: audio.cpp v0.8.2-audio8-perf-hotfix (the GGUF's own runtime, not vibevoice.cpp) on cuda 12.8 runtime + libgomp + libsoxr, sha256-pinned; :8031 direct. LibriSpeech WER 3/69, RTF 0.07-0.14; ~31 s cold first request.
51 lines
2.0 KiB
YAML
51 lines
2.0 KiB
YAML
# vibevoice-asr-seat — Microsoft VibeVoice-ASR-Streaming-1.5B on nh3-ml1 (CT 109,
|
|
# RTX 2000E Ada 16 GB), served by audio.cpp. Utility seat for brokkr's dataset
|
|
# foundry (speech → text, speaker-attributed), operator-approved 2026-09-26
|
|
# (relayed by brokkr-smithy-dev).
|
|
#
|
|
# audiocpp_server vibevoice-asr-streaming-1.5b (Q4_K) :8031
|
|
# POST /v1/audio/transcriptions (OpenAI-style, whole file)
|
|
# POST /v1/audio/transcriptions/live?... (chunked 16 kHz s16le PCM)
|
|
# GET /v1/models, /health
|
|
#
|
|
# Runtime is audio.cpp, per the GGUF's own model card (the GGUF is an audio.cpp
|
|
# package with its sidecars embedded, so no separate tokenizer file). It is NOT
|
|
# vanilla llama.cpp and NOT mudler's vibevoice.cpp.
|
|
# Direct access only; no gateway entry.
|
|
#
|
|
# Files (not in git): /opt/aimodels/gguf/vibevoice-asr-streaming-1.5b/ from
|
|
# christopherthompson81/VibeVoice-ASR-Streaming-1.5B-GGUF @ ff9615110299.
|
|
name: vibevoice-asr-seat
|
|
services:
|
|
audiocpp:
|
|
build:
|
|
context: .
|
|
image: local/audiocpp:v0.8.2-audio8-perf-hotfix
|
|
container_name: vibevoice-asr
|
|
restart: unless-stopped
|
|
command: ["--config", "/config/server.json", "--no-ui", "--log"]
|
|
ports:
|
|
- "${ASR_PORT}:8080"
|
|
volumes:
|
|
- /opt/aimodels/gguf/vibevoice-asr-streaming-1.5b:/models:ro
|
|
- /opt/docker/conf/vibevoice-asr-seat/server.json:/config/server.json:ro
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
device_ids: ["0"]
|
|
capabilities: [gpu]
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-fsS", "http://localhost:8080/health"]
|
|
interval: 30s
|
|
timeout: 10s
|
|
retries: 3
|
|
start_period: 120s
|
|
labels:
|
|
- homepage.group=AI - Eval & Retrieval
|
|
- homepage.name=ASR — VibeVoice Streaming 1.5B (audio.cpp, nh3-ml1)
|
|
- homepage.icon=mdi-microphone-message
|
|
- homepage.description=Streaming speech-to-text for the dataset foundry (direct, no gateway)
|
|
- homepage.href=http://10.100.50.80:${ASR_PORT}/v1/models
|