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:
asr:
image: soar97/triton-sensevoice:24.05
ports:
- "10085:8000"
- "10086:8001"
- "10087:8002"
environment:
- PYTHONIOENCODING=utf-8
deploy:
resources:
reservations:
devices:
- driver: nvidia
device_ids: ['0']
capabilities: [gpu]
command: >
/bin/bash -c "cd ./model_repo_sense_voice_small && bash run.sh"