websocket

游雁

2024-01-31 e2154e45996318c245b100d204bbb0ebdc8cadbe

websocket

 runtime/python/websocket/funasr_client_api.py

@@ -5,7 +5,7 @@
  2022-2023 by zhaomingwork@qq.com  

'''

# pip install websocket-client

import  ssl

import ssl

from websocket import ABNF

from websocket import create_connection

from queue import Queue

@@ -20,7 +20,13 @@
    python asr recognizer lib



    '''

    def __init__(self, host="127.0.0.1", port="30035", is_ssl=True,chunk_size="5, 10, 5",chunk_interval=10,mode="offline",wav_name="default"):

    def __init__(self, host="127.0.0.1",

                 port="30035",

                 is_ssl=True,

                 chunk_size="0, 10, 5",

                 chunk_interval=10,

                 mode="offline",

                 wav_name="default"):

      '''

          host: server host ip

          port: server port

@@ -43,17 +49,21 @@
        self.msg_queue = Queue() # used for recognized result text



        print("connect to url",uri)

        self.websocket=create_connection(uri,ssl=ssl_context,sslopt=ssl_opt)

        self.websocket=create_connection(uri, ssl=ssl_context, sslopt=ssl_opt)

 

        self.thread_msg = threading.Thread(target=Funasr_websocket_recognizer.thread_rec_msg,args=(self,))

        self.thread_msg = threading.Thread(target=Funasr_websocket_recognizer.thread_rec_msg, args=(self,))

        self.thread_msg.start()

        chunk_size = [int(x) for x in  chunk_size.split(",")]

        stride = int(60 *  chunk_size[1]/  chunk_interval / 1000 * 16000 * 2)

        stride = int(60 *  chunk_size[1] / chunk_interval / 1000 * 16000 * 2)

        chunk_num = (len(audio_bytes) - 1) // stride + 1

       

        message = json.dumps({"mode": args.mode, "chunk_size": args.chunk_size, "encoder_chunk_look_back": 4,

                              "decoder_chunk_look_back": 1, "chunk_interval": args.chunk_interval, 
                              "wav_name": wav_name, "is_speaking": True})

        message = json.dumps({"mode": mode,

                              "chunk_size": chunk_size,

                              "encoder_chunk_look_back": 4,

                              "decoder_chunk_look_back": 1,

                              "chunk_interval": chunk_interval,

                              "wav_name": wav_name,

                              "is_speaking": True})

 

        self.websocket.send(message)

 

@@ -68,7 +78,7 @@
        try:

         while(True):

           msg=self.websocket.recv()

           if msg is None or len(msg)==0:

           if msg is None or len(msg) == 0:

             continue

           msg = json.loads(msg)

           

@@ -77,7 +87,7 @@
            print("client closed")

 

    # feed data to asr engine, wait_time means waiting for result until time out

    def feed_chunk(self, chunk,wait_time=0.01):

    def feed_chunk(self, chunk, wait_time=0.01):

        try:

            self.websocket.send(chunk,  ABNF.OPCODE_BINARY)

            # loop to check if there is a message, timeout in 0.01s

@@ -89,6 +99,7 @@
            return msg

        except:

            return ""

        
    def close(self,timeout=1):

        message = json.dumps({"is_speaking": False})

        self.websocket.send(message)

@@ -103,9 +114,10 @@
        return msg

        

if __name__ == '__main__':

    
    print('example for Funasr_websocket_recognizer') 

    import wave

    wav_path="asr_example.wav"

    wav_path = "/Users/zhifu/Downloads/modelscope_models/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav"

    with wave.open(wav_path, "rb") as wav_file:

                params = wav_file.getparams()

                frames = wav_file.readframes(wav_file.getnframes())

@@ -115,20 +127,24 @@
    stride = int(60 * 10 / 10 / 1000 * 16000 * 2)

    chunk_num = (len(audio_bytes) - 1) // stride + 1

    # create an recognizer 

    rcg=Funasr_websocket_recognizer(host="127.0.0.1",port="30035",is_ssl=True,mode="2pass")

    rcg = Funasr_websocket_recognizer(host="127.0.0.1",

                                      port="10095",

                                      is_ssl=True,

                                      mode="2pass",

                                      chunk_size="0,10,5")

    # loop to send chunk

    for i in range(chunk_num):



            beg = i * stride

            data = audio_bytes[beg:beg + stride]

 

            text=rcg.feed_chunk(data,wait_time=0.02)

            text = rcg.feed_chunk(data,wait_time=0.02)

            if len(text)>0:

               print("text",text)

            time.sleep(0.05)

 

    # get last message

    text=rcg.close(timeout=3)

    text = rcg.close(timeout=3)

    print("text",text)

 

    


 runtime/python/websocket/funasr_wss_server.py

@@ -152,7 +152,7 @@
    frames_asr = []
    frames_asr_online = []
    global websocket_users
    await clear_websocket()
    # await clear_websocket()
    websocket_users.add(websocket)
    websocket.status_dict_asr = {}
    websocket.status_dict_asr_online = {"cache": {}, "is_final": False}