| | |
|---|
| | | |
|---|
| | | import logging |
|---|
| | | |
|---|
| | | SUPPORT_AUDIO_TYPE_SETS = ['.wav', '.pcm'] |
|---|
| | | logging.basicConfig(level=logging.ERROR) |
|---|
| | | |
|---|
| | | parser = argparse.ArgumentParser() |
|---|
| | |
|---|
| | | print(args) |
|---|
| | | # voices = asyncio.Queue() |
|---|
| | | from queue import Queue |
|---|
| | | |
|---|
| | | voices = Queue() |
|---|
| | | offline_msg_done=False |
|---|
| | | |
|---|
| | | ibest_writer = None |
|---|
| | | if args.output_dir is not None: |
|---|
| | | writer = DatadirWriter(args.output_dir) |
|---|
| | | ibest_writer = writer[f"1best_recog"] |
|---|
| | | |
|---|
| | | |
|---|
| | | async def record_microphone(): |
|---|
| | | is_finished = False |
|---|
| | |
|---|
| | | input=True, |
|---|
| | | frames_per_buffer=CHUNK) |
|---|
| | | |
|---|
| | | message = json.dumps({"mode": args.mode, "chunk_size": args.chunk_size, "chunk_interval": args.chunk_interval, "wav_name": "microphone", "is_speaking": True}) |
|---|
| | | message = json.dumps({"mode": args.mode, "chunk_size": args.chunk_size, "chunk_interval": args.chunk_interval, |
|---|
| | | "wav_name": "microphone", "is_speaking": True}) |
|---|
| | | voices.put(message) |
|---|
| | | while True: |
|---|
| | | |
|---|
| | | data = stream.read(CHUNK) |
|---|
| | | message = data |
|---|
| | | |
|---|
| | | voices.put(message) |
|---|
| | | |
|---|
| | | await asyncio.sleep(0.005) |
|---|
| | | |
|---|
| | | async def record_from_scp(chunk_begin,chunk_size): |
|---|
| | | import wave |
|---|
| | | global voices |
|---|
| | | is_finished = False |
|---|
| | | if args.audio_in.endswith(".scp"): |
|---|
| | |
|---|
| | | wavs=wavs[chunk_begin:chunk_begin+chunk_size] |
|---|
| | | for wav in wavs: |
|---|
| | | wav_splits = wav.strip().split() |
|---|
| | | |
|---|
| | | 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] |
|---|
| | | |
|---|
| | | # bytes_f = open(wav_path, "rb") |
|---|
| | | # bytes_data = bytes_f.read() |
|---|
| | | if not len(wav_path.strip())>0: |
|---|
| | | continue |
|---|
| | | if wav_path.endswith(".pcm"): |
|---|
| | | with open(wav_path, "rb") as f: |
|---|
| | | audio_bytes = f.read() |
|---|
| | | elif wav_path.endswith(".wav"): |
|---|
| | | import wave |
|---|
| | | with wave.open(wav_path, "rb") as wav_file: |
|---|
| | | params = wav_file.getparams() |
|---|
| | | # header_length = wav_file.getheaders()[0][1] |
|---|
| | | # wav_file.setpos(header_length) |
|---|
| | | frames = wav_file.readframes(wav_file.getnframes()) |
|---|
| | | |
|---|
| | | audio_bytes = bytes(frames) |
|---|
| | | else: |
|---|
| | | raise NotImplementedError( |
|---|
| | | f'Not supported audio type') |
|---|
| | | |
|---|
| | | # stride = int(args.chunk_size/1000*16000*2) |
|---|
| | | stride = int(60*args.chunk_size[1]/args.chunk_interval/1000*16000*2) |
|---|
| | | chunk_num = (len(audio_bytes)-1)//stride + 1 |
|---|
| | | # print(stride) |
|---|
| | | |
|---|
| | | # send first time |
|---|
| | | message = json.dumps({"mode": args.mode, "chunk_size": args.chunk_size, "chunk_interval": args.chunk_interval, "wav_name": wav_name,"is_speaking": True}) |
|---|
| | | voices.put(message) |
|---|
| | | message = json.dumps({"mode": args.mode, "chunk_size": args.chunk_size, "chunk_interval": args.chunk_interval, |
|---|
| | | "wav_name": wav_name, "is_speaking": True}) |
|---|
| | | #voices.put(message) |
|---|
| | | await websocket.send(message) |
|---|
| | | is_speaking = True |
|---|
| | | for i in range(chunk_num): |
|---|
| | | |
|---|
| | | beg = i*stride |
|---|
| | | data = audio_bytes[beg:beg+stride] |
|---|
| | | message = data |
|---|
| | | voices.put(message) |
|---|
| | | #voices.put(message) |
|---|
| | | await websocket.send(message) |
|---|
| | | if i == chunk_num-1: |
|---|
| | | is_speaking = False |
|---|
| | | message = json.dumps({"is_speaking": is_speaking}) |
|---|
| | | voices.put(message) |
|---|
| | | # print("data_chunk: ", len(data_chunk)) |
|---|
| | | # print(voices.qsize()) |
|---|
| | | #voices.put(message) |
|---|
| | | await websocket.send(message) |
|---|
| | | |
|---|
| | | sleep_duration = 0.001 if args.send_without_sleep else 60*args.chunk_size[1]/args.chunk_interval/1000 |
|---|
| | | await asyncio.sleep(sleep_duration) |
|---|
| | | |
|---|
| | | |
|---|
| | | async def ws_send(): |
|---|
| | | global voices |
|---|
| | | global websocket |
|---|
| | | print("started to sending data!") |
|---|
| | | while True: |
|---|
| | | # when all data sent, we need to close websocket |
|---|
| | | while not voices.empty(): |
|---|
| | | data = voices.get() |
|---|
| | | voices.task_done() |
|---|
| | | try: |
|---|
| | | await websocket.send(data) |
|---|
| | | except Exception as e: |
|---|
| | | print('Exception occurred:', e) |
|---|
| | | traceback.print_exc() |
|---|
| | | exit(0) |
|---|
| | | await asyncio.sleep(0.005) |
|---|
| | | await asyncio.sleep(0.005) |
|---|
| | | await asyncio.sleep(1) |
|---|
| | | await asyncio.sleep(3) |
|---|
| | | # offline model need to wait for message recved |
|---|
| | | |
|---|
| | | if args.mode=="offline": |
|---|
| | | global offline_msg_done |
|---|
| | | while not offline_msg_done: |
|---|
| | | await asyncio.sleep(1) |
|---|
| | | |
|---|
| | | await websocket.close() |
|---|
| | | |
|---|
| | | |
|---|
| | | |
|---|
| | | |
|---|
| | | |
|---|
| | | |
|---|
| | | async def message(id): |
|---|
| | | global websocket |
|---|
| | | global websocket,voices,offline_msg_done |
|---|
| | | text_print = "" |
|---|
| | | text_print_2pass_online = "" |
|---|
| | | text_print_2pass_offline = "" |
|---|
| | | while True: |
|---|
| | | try: |
|---|
| | | while True: |
|---|
| | | |
|---|
| | | meg = await websocket.recv() |
|---|
| | | meg = json.loads(meg) |
|---|
| | | wav_name = meg.get("wav_name", "demo") |
|---|
| | | # print(wav_name) |
|---|
| | | text = meg["text"] |
|---|
| | | if ibest_writer is not None: |
|---|
| | | ibest_writer["text"][wav_name] = text |
|---|
| | |
|---|
| | | text_print = text_print[-args.words_max_print:] |
|---|
| | | os.system('clear') |
|---|
| | | print("\rpid"+str(id)+": "+text_print) |
|---|
| | | offline_msg_done=True |
|---|
| | | else: |
|---|
| | | if meg["mode"] == "2pass-online": |
|---|
| | | text_print_2pass_online += "{}".format(text) |
|---|
| | |
|---|
| | | |
|---|
| | | except Exception as e: |
|---|
| | | print("Exception:", e) |
|---|
| | | traceback.print_exc() |
|---|
| | | exit(0) |
|---|
| | | #traceback.print_exc() |
|---|
| | | #await websocket.close() |
|---|
| | | |
|---|
| | | |
|---|
| | | |
|---|
| | | async def print_messge(): |
|---|
| | | global websocket |
|---|
| | |
|---|
| | | print(meg) |
|---|
| | | except Exception as e: |
|---|
| | | print("Exception:", e) |
|---|
| | | traceback.print_exc() |
|---|
| | | #traceback.print_exc() |
|---|
| | | exit(0) |
|---|
| | | |
|---|
| | | async def ws_client(id,chunk_begin,chunk_size): |
|---|
| | | global websocket |
|---|
| | | if args.audio_in is None: |
|---|
| | | chunk_begin=0 |
|---|
| | | chunk_size=1 |
|---|
| | | global websocket,voices,offline_msg_done |
|---|
| | | |
|---|
| | | for i in range(chunk_begin,chunk_begin+chunk_size): |
|---|
| | | offline_msg_done=False |
|---|
| | | voices = Queue() |
|---|
| | | if args.ssl==1: |
|---|
| | | ssl_context = ssl.SSLContext() |
|---|
| | | ssl_context.check_hostname = False |
|---|
| | |
|---|
| | | uri = "ws://{}:{}".format(args.host, args.port) |
|---|
| | | ssl_context=None |
|---|
| | | print("connect to",uri) |
|---|
| | | async for websocket in websockets.connect(uri, subprotocols=["binary"], ping_interval=None,ssl=ssl_context): |
|---|
| | | async with websockets.connect(uri, subprotocols=["binary"], ping_interval=None, ssl=ssl_context) as websocket: |
|---|
| | | if args.audio_in is not None: |
|---|
| | | task = asyncio.create_task(record_from_scp(chunk_begin,chunk_size)) |
|---|
| | | task = asyncio.create_task(record_from_scp(i, 1)) |
|---|
| | | else: |
|---|
| | | task = asyncio.create_task(record_microphone()) |
|---|
| | | task2 = asyncio.create_task(ws_send()) |
|---|
| | | task3 = asyncio.create_task(message(id)) |
|---|
| | | await asyncio.gather(task, task2, task3) |
|---|
| | | #task2 = asyncio.create_task(ws_send()) |
|---|
| | | task3 = asyncio.create_task(message(str(id)+"_"+str(i))) #processid+fileid |
|---|
| | | await asyncio.gather(task, task3) |
|---|
| | | exit(0) |
|---|
| | | |
|---|
| | | |
|---|
| | | def one_thread(id,chunk_begin,chunk_size): |
|---|
| | | asyncio.get_event_loop().run_until_complete(ws_client(id,chunk_begin,chunk_size)) |
|---|
| | | asyncio.get_event_loop().run_forever() |
|---|
| | | |
|---|
| | | |
|---|
| | | if __name__ == '__main__': |
|---|
| | | # for microphone |
|---|
| | |
|---|
| | | wavs = f_scp.readlines() |
|---|
| | | else: |
|---|
| | | wavs = [args.audio_in] |
|---|
| | | for wav in wavs: |
|---|
| | | wav_splits = wav.strip().split() |
|---|
| | | 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.test_thread_num: |
|---|
| | | chunk_size=int((total_len)/args.test_thread_num) |
|---|
| | | chunk_size = int(total_len / args.test_thread_num) |
|---|
| | | remain_wavs=total_len-chunk_size*args.test_thread_num |
|---|
| | | else: |
|---|
| | | chunk_size=1 |
|---|
| | |
|---|
| | | p.join() |
|---|
| | | |
|---|
| | | print('end') |
|---|
| | | |
|---|
| | | |
|---|
