43 lines
1.6 KiB
Plaintext
43 lines
1.6 KiB
Plaintext
# Local model assets; model loading never downloads weights at startup.
|
|
MODEL_DIR=models
|
|
# Set this if CAM++ is not under the path declared in model_manifest.json.
|
|
# CAM_MODEL_PATH=iic/speech_campplus_sv_zh-cn_16k-common
|
|
|
|
# Local FunASR streaming ASR and VAD models.
|
|
FUNASR_ASR_MODEL=paraformer-zh-streaming
|
|
FUNASR_VAD_MODEL=fsmn-vad
|
|
FUNASR_DEVICE=cuda:0
|
|
FUNASR_VAD_DEVICE=cpu
|
|
# Silence duration in milliseconds before FSMN VAD finalizes a speech segment.
|
|
# Strategy 0 (semantic sentence) defaults to 800 ms; increase to preserve pauses.
|
|
FUNASR_VAD_MAX_END_SILENCE_MS=800
|
|
# Strategy 1 (paragraph) keeps the longer 5 s pause. Adjust independently if needed.
|
|
FUNASR_VAD_PARAGRAPH_MAX_END_SILENCE_MS=5000
|
|
# Higher margins reject more weak background noise but can suppress quiet speech.
|
|
FUNASR_VAD_SPEECH_NOISE_THRES=0.6
|
|
|
|
# Native FunASR WSS chunk settings. The middle chunk is sent as 10 x 60 ms.
|
|
FUNASR_CHUNK_SIZE=0,10,5
|
|
FUNASR_CHUNK_INTERVAL=10
|
|
FUNASR_ENCODER_LOOK_BACK=4
|
|
FUNASR_DECODER_LOOK_BACK=1
|
|
FUNASR_FINALIZE_TIMEOUT_SECONDS=300
|
|
FUNASR_NATIVE_WS_HOST=127.0.0.1
|
|
FUNASR_NATIVE_WS_PORT=10095
|
|
|
|
# CAM++ is required and started by backend/run_backend.py.
|
|
AUXILIARY_SERVICE_URL=http://127.0.0.1:8010
|
|
AUXILIARY_DEVICE=cpu
|
|
AUXILIARY_PRELOAD_KINDS=speaker_verification
|
|
# Optional punctuation runs on CPU by default so the speaker model can retain GPU memory.
|
|
FUNASR_PUNC_DEVICE=cpu
|
|
|
|
# Frontend and backend run independently. The frontend proxies /ws and /api/stop.
|
|
FRONTEND_HOST=127.0.0.1
|
|
FRONTEND_PORT=8080
|
|
BACKEND_INTERNAL_URL=http://127.0.0.1:8082
|
|
BACKEND_PUBLIC_URL=http://127.0.0.1:8082
|
|
WEB_HOST=0.0.0.0
|
|
WEB_PORT=8082
|
|
WEB_DISPLAY_HOST=127.0.0.1
|