Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add

游雁

2023-08-30 c2e4e3c2e9be855277d9f4fa9cd0544892ff829a

 funasr/runtime/python/websocket/funasr_wss_client.py

@@ -12,7 +12,6 @@

import logging

SUPPORT_AUDIO_TYPE_SETS = ['.wav', '.pcm']
logging.basicConfig(level=logging.ERROR)

parser = argparse.ArgumentParser()
@@ -177,10 +176,9 @@
            sleep_duration = 0.001 if args.mode == "offline" else 60 * args.chunk_size[1] / args.chunk_interval / 1000
            
            await asyncio.sleep(sleep_duration)
    # when all data sent, we need to close websocket
    while not voices.empty():
         await asyncio.sleep(1)
    await asyncio.sleep(3)
    
    if not args.mode=="offline":
        await asyncio.sleep(2)
    # offline model need to wait for message recved
    
    if args.mode=="offline":
@@ -198,7 +196,7 @@
    text_print_2pass_online = ""
    text_print_2pass_offline = ""
    if args.output_dir is not None:
        ibest_writer = open(os.path.join(args.output_dir, "text.{}".format(id)), "w+", encoding="utf-8")
        ibest_writer = open(os.path.join(args.output_dir, "text.{}".format(id)), "a", encoding="utf-8")
    else:
        ibest_writer = None
    try:
@@ -206,6 +204,7 @@
        
            meg = await websocket.recv()
            meg = json.loads(meg)
            # print(meg)
            wav_name = meg.get("wav_name", "demo")
            text = meg["text"]

@@ -220,10 +219,14 @@
                print("\rpid" + str(id) + ": " + text_print)
            elif meg["mode"] == "offline":
                text_print += "{}".format(text)
                text_print = text_print[-args.words_max_print:]
                # text_print = text_print[-args.words_max_print:]
                # os.system('clear')
                print("\rpid" + str(id) + ": " + text_print)
                offline_msg_done=True
                print("\rpid" + str(id) + ": " + wav_name + ": " + text_print)
                if ("is_final" in meg and meg["is_final"]==False):
                    offline_msg_done = True
                
                if not "is_final" in meg:
                    offline_msg_done = True
            else:
                if meg["mode"] == "2pass-online":
                    text_print_2pass_online += "{}".format(text)
@@ -296,9 +299,7 @@
            wav_name = wav_splits[0] if len(wav_splits) > 1 else "demo"
            wav_path = wav_splits[1] if len(wav_splits) > 1 else wav_splits[0]
            audio_type = os.path.splitext(wav_path)[-1].lower()
            # if audio_type not in SUPPORT_AUDIO_TYPE_SETS:
            #    raise NotImplementedError(
            #        f'Not supported audio type: {audio_type}')


        total_len = len(wavs)
        if total_len >= args.thread_num: