Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
services:
funasr-moss-api:
build:
context: ../..
dockerfile: examples/openai_api/Dockerfile.moss
image: funasr-moss-api:local
ports:
- "${FUNASR_HOST_PORT:-8000}:8000"
environment:
FUNASR_PORT: "8000"
FUNASR_DEVICE: "${FUNASR_DEVICE:-cuda:0}"
FUNASR_MODEL: moss-transcribe-diarize
HF_HOME: /root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
volumes:
- funasr-moss-cache:/root/.cache
shm_size: "8gb"
volumes:
funasr-moss-cache: