| | |
|---|
| | | 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 |
|---|
| | |
|---|
| | | print("model loading") |
|---|
| | | |
|---|
| | | inference_pipeline_asr_online = pipeline( |
|---|
| | | task=Tasks.auto_speech_recognition, |
|---|
| | | model=args.asr_model_online, |
|---|
| | | ngpu=args.ngpu, |
|---|
| | | ncpu=args.ncpu, |
|---|
| | | model_revision='v1.0.4') |
|---|
| | | task=Tasks.auto_speech_recognition, |
|---|
| | | model=args.asr_model_online, |
|---|
| | | ngpu=args.ngpu, |
|---|
| | | ncpu=args.ncpu, |
|---|
| | | model_revision='v1.0.4') |
|---|
| | | |
|---|
| | | print("model loaded") |
|---|
| | | |
|---|
| | | |
|---|
| | | |
|---|
| | | async def ws_serve(websocket, path): |
|---|
| | | frames_online = [] |
|---|
| | | global websocket_users |
|---|
| | | websocket.send_msg = Queue() |
|---|
| | | websocket_users.add(websocket) |
|---|
| | | websocket.param_dict_asr_online = {"cache": dict()} |
|---|
| | | websocket.speek_online = Queue() |
|---|
| | | |
|---|
| | | try: |
|---|
| | | async for message in websocket: |
|---|
| | | message = json.loads(message) |
|---|
| | | is_finished = message["is_finished"] |
|---|
| | | if not is_finished: |
|---|
| | | audio = bytes(message['audio'], 'ISO-8859-1') |
|---|
| | | |
|---|
| | | is_speaking = message["is_speaking"] |
|---|
| | | websocket.param_dict_asr_online["is_final"] = not is_speaking |
|---|
| | | |
|---|
| | | websocket.param_dict_asr_online["chunk_size"] = message["chunk_size"] |
|---|
| | | |
|---|
| | | frames_online.append(audio) |
|---|
| | | if len(frames_online) % message["chunk_interval"] == 0 or not is_speaking: |
|---|
| | | audio_in = b"".join(frames_online) |
|---|
| | | await async_asr_online(websocket,audio_in) |
|---|
| | | frames_online = [] |
|---|
| | | frames_asr_online = [] |
|---|
| | | global websocket_users |
|---|
| | | websocket_users.add(websocket) |
|---|
| | | websocket.param_dict_asr_online = {"cache": dict()} |
|---|
| | | websocket.wav_name = "microphone" |
|---|
| | | print("new user connected",flush=True) |
|---|
| | | try: |
|---|
| | | async for message in websocket: |
|---|
| | | |
|---|
| | | |
|---|
| | | if isinstance(message, str): |
|---|
| | | messagejson = json.loads(message) |
|---|
| | | |
|---|
| | | if "is_speaking" in messagejson: |
|---|
| | | websocket.is_speaking = messagejson["is_speaking"] |
|---|
| | | websocket.param_dict_asr_online["is_final"] = not websocket.is_speaking |
|---|
| | | # need to fire engine manually if no data received any more |
|---|
| | | if not websocket.is_speaking: |
|---|
| | | await async_asr_online(websocket,b"") |
|---|
| | | if "chunk_interval" in messagejson: |
|---|
| | | websocket.chunk_interval=messagejson["chunk_interval"] |
|---|
| | | if "wav_name" in messagejson: |
|---|
| | | websocket.wav_name = messagejson.get("wav_name") |
|---|
| | | if "chunk_size" in messagejson: |
|---|
| | | websocket.param_dict_asr_online["chunk_size"] = messagejson["chunk_size"] |
|---|
| | | # if has bytes in buffer or message is bytes |
|---|
| | | if len(frames_asr_online) > 0 or not isinstance(message, str): |
|---|
| | | if not isinstance(message,str): |
|---|
| | | frames_asr_online.append(message) |
|---|
| | | if len(frames_asr_online) % websocket.chunk_interval == 0 or not websocket.is_speaking: |
|---|
| | | audio_in = b"".join(frames_asr_online) |
|---|
| | | # if not websocket.is_speaking: |
|---|
| | | #padding 0.5s at end gurantee that asr engine can fire out last word |
|---|
| | | # audio_in=audio_in+b''.join(np.zeros(int(16000*0.5),dtype=np.int16)) |
|---|
| | | await async_asr_online(websocket,audio_in) |
|---|
| | | frames_asr_online = [] |
|---|
| | | |
|---|
| | | |
|---|
| | | except websockets.ConnectionClosed: |
|---|
| | | print("ConnectionClosed...", websocket_users) |
|---|
| | | websocket_users.remove(websocket) |
|---|
| | | except websockets.InvalidState: |
|---|
| | | print("InvalidState...") |
|---|
| | | except Exception as e: |
|---|
| | | print("Exception:", e) |
|---|
| | | |
|---|
| | | |
|---|
| | | |
|---|
| | | except websockets.ConnectionClosed: |
|---|
| | | print("ConnectionClosed...", websocket_users) |
|---|
| | | websocket_users.remove(websocket) |
|---|
| | | except websockets.InvalidState: |
|---|
| | | print("InvalidState...") |
|---|
| | | except Exception as e: |
|---|
| | | print("Exception:", e) |
|---|
| | | |
|---|
| | | async def async_asr_online(websocket,audio_in): |
|---|
| | | if len(audio_in) > 0: |
|---|
| | | audio_in = load_bytes(audio_in) |
|---|
| | | rec_result = inference_pipeline_asr_online(audio_in=audio_in, |
|---|
| | | param_dict=websocket.param_dict_asr_online) |
|---|
| | | if websocket.param_dict_asr_online["is_final"]: |
|---|
| | | 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": |
|---|
| | | if len(rec_result["text"])>0: |
|---|
| | | rec_result["text"][0]=rec_result["text"][0] #.replace(" ","") |
|---|
| | | message = json.dumps({"mode": "online", "text": rec_result["text"]}) |
|---|
| | | await websocket.send(message) |
|---|
| | | if len(audio_in) >=0: |
|---|
| | | audio_in = load_bytes(audio_in) |
|---|
| | | rec_result = inference_pipeline_asr_online(audio_in=audio_in, |
|---|
| | | param_dict=websocket.param_dict_asr_online) |
|---|
| | | if websocket.param_dict_asr_online.get("is_final", False): |
|---|
| | | 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": |
|---|
| | | message = json.dumps({"mode": "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) |
|---|
| | | |
|---|
| | | start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None) |
|---|
| | | # Generate with Lets Encrypt, copied to this location, chown to current user and 400 permissions |
|---|
| | | ssl_cert = args.certfile |
|---|
| | | ssl_key = args.keyfile |
|---|
| | | |
|---|
| | | 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() |
|---|
