docs

游雁

2023-05-25 b18f7d121f2f17df8bf2d0c2bbb223bc5ddbcc0f

 funasr/runtime/python/websocket/ws_server_2pass.py

@@ -5,7 +5,7 @@
import logging
import tracemalloc
import numpy as np

import ssl
from parse_args import args
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
@@ -46,7 +46,7 @@
    inference_pipeline_punc = pipeline(
        task=Tasks.punctuation,
        model=args.punc_model,
        model_revision=None,
        model_revision="v1.0.2",
        ngpu=args.ngpu,
        ncpu=args.ncpu,
    )
@@ -74,6 +74,7 @@
    websocket.param_dict_punc = {'cache': list()}
    websocket.vad_pre_idx = 0
    speech_start = False
    speech_end_i = False
    websocket.wav_name = "microphone"
    print("new user connected", flush=True)

@@ -99,7 +100,9 @@
        
                    # asr online
                    frames_asr_online.append(message)
                    if len(frames_asr_online) % websocket.chunk_interval == 0:
                    websocket.param_dict_asr_online["is_final"] = speech_end_i
                    if len(frames_asr_online) % websocket.chunk_interval == 0 or websocket.param_dict_asr_online["is_final"]:
                        
                        audio_in = b"".join(frames_asr_online)
                        await async_asr_online(websocket, audio_in)
                        frames_asr_online = []
@@ -115,12 +118,13 @@
                        frames_asr.extend(frames_pre)
                # asr punc offline
                if speech_end_i or not websocket.is_speaking:
                    # print("vad end point")
                    audio_in = b"".join(frames_asr)
                    await async_asr(websocket, audio_in)
                    frames_asr = []
                    speech_start = False
                    frames_asr_online = []
                    websocket.param_dict_asr_online = {"cache": dict()}
                    # frames_asr_online = []
                    # websocket.param_dict_asr_online = {"cache": dict()}
                    if not websocket.is_speaking:
                        websocket.vad_pre_idx = 0
                        frames = []
@@ -166,24 +170,37 @@
                    rec_result = inference_pipeline_punc(text_in=rec_result['text'],
                                                         param_dict=websocket.param_dict_punc)
                    # print("offline", rec_result)
                message = json.dumps({"mode": "2pass-offline", "text": rec_result["text"], "wav_name": websocket.wav_name})
                await websocket.send(message)
                if 'text' in rec_result:
                    message = json.dumps({"mode": "2pass-offline", "text": rec_result["text"], "wav_name": websocket.wav_name})
                    await websocket.send(message)


async def async_asr_online(websocket, audio_in):
    if len(audio_in) > 0:
        audio_in = load_bytes(audio_in)
        # print(websocket.param_dict_asr_online.get("is_final", False))
        rec_result = inference_pipeline_asr_online(audio_in=audio_in,
                                                   param_dict=websocket.param_dict_asr_online)
        # print(rec_result)
        if websocket.param_dict_asr_online.get("is_final", False):
            websocket.param_dict_asr_online["cache"] = dict()
            return
            #     websocket.param_dict_asr_online["cache"] = dict()
        if "text" in rec_result:
            if rec_result["text"] != "sil" and rec_result["text"] != "waiting_for_more_voice":
                # print("online", rec_result)
                message = json.dumps({"mode": "2pass-online", "text": rec_result["text"], "wav_name": websocket.wav_name})
                await websocket.send(message)

if len(args.certfile)>0:
   ssl_context = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
	
   # Generate with Lets Encrypt, copied to this location, chown to current user and 400 permissions
   ssl_cert = args.certfile
   ssl_key = args.keyfile

start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None)
   ssl_context.load_cert_chain(ssl_cert, keyfile=ssl_key)
   start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None,ssl=ssl_context)
else:
   start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None)
asyncio.get_event_loop().run_until_complete(start_server)
asyncio.get_event_loop().run_forever()