From 6427c834dfd97b1f05c6659cdc7ccf010bf82fe1 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期一, 24 四月 2023 19:50:07 +0800
Subject: [PATCH] update
---
funasr/runtime/python/websocket/ASR_server.py | 208 ++++++++++++++++++++++++++-------------------------
1 files changed, 107 insertions(+), 101 deletions(-)
diff --git a/funasr/runtime/python/websocket/ASR_server.py b/funasr/runtime/python/websocket/ASR_server.py
index cfa9a42..827df7b 100644
--- a/funasr/runtime/python/websocket/ASR_server.py
+++ b/funasr/runtime/python/websocket/ASR_server.py
@@ -1,18 +1,22 @@
-# server.py 娉ㄦ剰鏈緥浠呭鐞嗗崟涓猚lent鍙戦�佺殑璇煶鏁版嵁锛屽苟鏈澶歝lient杩炴帴杩涜鍒ゆ柇鍜屽鐞�
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-from modelscope.utils.logger import get_logger
-import logging
-
-logger = get_logger(log_level=logging.CRITICAL)
-logger.setLevel(logging.CRITICAL)
-
import asyncio
import websockets
import time
from queue import Queue
import threading
import argparse
+
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+from modelscope.utils.logger import get_logger
+import logging
+import tracemalloc
+tracemalloc.start()
+
+logger = get_logger(log_level=logging.CRITICAL)
+logger.setLevel(logging.CRITICAL)
+
+
+websocket_users = set() #缁存姢瀹㈡埛绔垪琛�
parser = argparse.ArgumentParser()
parser.add_argument("--host",
@@ -46,51 +50,122 @@
args = parser.parse_args()
print("model loading")
-voices = Queue()
-speek = Queue()
+
-# 鍒涘缓涓�涓猇AD瀵硅薄
-vad_pipline = pipeline(
+# vad
+inference_pipeline_vad = pipeline(
task=Tasks.voice_activity_detection,
model=args.vad_model,
- model_revision="v1.2.0",
+ model_revision=None,
output_dir=None,
batch_size=1,
- mode='online'
+ mode='online',
+ ngpu=args.ngpu,
)
-param_dict_vad = {'in_cache': dict(), "is_final": False}
+# param_dict_vad = {'in_cache': dict(), "is_final": False}
-# 鍒涘缓涓�涓狝SR瀵硅薄
-param_dict = dict()
+# asr
+param_dict_asr = {}
# param_dict["hotword"] = "灏忎簲 灏忎簲鏈�" # 璁剧疆鐑瘝锛岀敤绌烘牸闅斿紑
-inference_pipeline2 = pipeline(
+inference_pipeline_asr = pipeline(
task=Tasks.auto_speech_recognition,
model=args.asr_model,
- param_dict=param_dict,
+ param_dict=param_dict_asr,
+ ngpu=args.ngpu,
)
+if args.punc_model != "":
+ # param_dict_punc = {'cache': list()}
+ inference_pipeline_punc = pipeline(
+ task=Tasks.punctuation,
+ model=args.punc_model,
+ model_revision=None,
+ ngpu=args.ngpu,
+ )
+else:
+ inference_pipeline_punc = None
+
print("model loaded")
async def ws_serve(websocket, path):
- global voices
+ #speek = Queue()
+ frames = [] # 瀛樺偍鎵�鏈夌殑甯ф暟鎹�
+ buffer = [] # 瀛樺偍缂撳瓨涓殑甯ф暟鎹紙鏈�澶氫袱涓墖娈碉級
+ RECORD_NUM = 0
+ global websocket_users
+ speech_start, speech_end = False, False
+ # 璋冪敤asr鍑芥暟
+ websocket.param_dict_vad = {'in_cache': dict(), "is_final": False}
+ websocket.param_dict_punc = {'cache': list()}
+ websocket.speek = Queue() #websocket 娣诲姞杩涢槦鍒楀璞� 璁゛sr璇诲彇璇煶鏁版嵁鍖�
+ websocket.send_msg = Queue() #websocket 娣诲姞涓槦鍒楀璞� 璁﹚s鍙戦�佹秷鎭埌瀹㈡埛绔�
+ websocket_users.add(websocket)
+ ss = threading.Thread(target=asr, args=(websocket,))
+ ss.start()
+
try:
async for message in websocket:
- voices.put(message)
+ #voices.put(message)
#print("put")
- except websockets.exceptions.ConnectionClosedError as e:
- print('Connection closed with exception:', e)
+ #await websocket.send("123")
+ buffer.append(message)
+ if len(buffer) > 2:
+ buffer.pop(0) # 濡傛灉缂撳瓨瓒呰繃涓や釜鐗囨锛屽垯鍒犻櫎鏈�鏃╃殑涓�涓�
+
+ if speech_start:
+ frames.append(message)
+ RECORD_NUM += 1
+ speech_start_i, speech_end_i = vad(message, websocket)
+ #print(speech_start_i, speech_end_i)
+ if speech_start_i:
+ speech_start = speech_start_i
+ frames = []
+ frames.extend(buffer) # 鎶婁箣鍓�2涓闊虫暟鎹揩鍔犲叆
+ if speech_end_i or RECORD_NUM > 300:
+ speech_start = False
+ audio_in = b"".join(frames)
+ websocket.speek.put(audio_in)
+ frames = [] # 娓呯┖鎵�鏈夌殑甯ф暟鎹�
+ buffer = [] # 娓呯┖缂撳瓨涓殑甯ф暟鎹紙鏈�澶氫袱涓墖娈碉級
+ RECORD_NUM = 0
+ if not websocket.send_msg.empty():
+ await websocket.send(websocket.send_msg.get())
+ websocket.send_msg.task_done()
+
+
+ except websockets.ConnectionClosed:
+ print("ConnectionClosed...", websocket_users) # 閾炬帴鏂紑
+ websocket_users.remove(websocket)
+ except websockets.InvalidState:
+ print("InvalidState...") # 鏃犳晥鐘舵��
except Exception as e:
- print('Exception occurred:', e)
+ print("Exception:", e)
+
-start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None)
+def asr(websocket): # ASR鎺ㄧ悊
+ global inference_pipeline_asr, inference_pipeline_punc
+ # global param_dict_punc
+ global websocket_users
+ while websocket in websocket_users:
+ if not websocket.speek.empty():
+ audio_in = websocket.speek.get()
+ websocket.speek.task_done()
+ if len(audio_in) > 0:
+ rec_result = inference_pipeline_asr(audio_in=audio_in)
+ if inference_pipeline_punc is not None and 'text' in rec_result:
+ rec_result = inference_pipeline_punc(text_in=rec_result['text'], param_dict=websocket.param_dict_punc)
+ # print(rec_result)
+ if "text" in rec_result:
+ websocket.send_msg.put(rec_result["text"]) # 瀛樺叆鍙戦�侀槦鍒� 鐩存帴璋冪敤send鍙戦�佷笉浜�
+
+ time.sleep(0.1)
-
-def vad(data): # 鎺ㄧ悊
- global vad_pipline, param_dict_vad
+def vad(data, websocket): # VAD鎺ㄧ悊
+ global inference_pipeline_vad
#print(type(data))
# print(param_dict_vad)
- segments_result = vad_pipline(audio_in=data, param_dict=param_dict_vad)
+ segments_result = inference_pipeline_vad(audio_in=data, param_dict=websocket.param_dict_vad)
# print(segments_result)
# print(param_dict_vad)
speech_start = False
@@ -104,76 +179,7 @@
speech_end = True
return speech_start, speech_end
-def asr(): # 鎺ㄧ悊
- global inference_pipeline2
- global speek
- while True:
- while not speek.empty():
- audio_in = speek.get()
- speek.task_done()
- rec_result = inference_pipeline2(audio_in=audio_in)
- print(rec_result)
- time.sleep(0.1)
- time.sleep(0.1)
-
-
-def main(): # 鎺ㄧ悊
- frames = [] # 瀛樺偍鎵�鏈夌殑甯ф暟鎹�
- buffer = [] # 瀛樺偍缂撳瓨涓殑甯ф暟鎹紙鏈�澶氫袱涓墖娈碉級
- # silence_count = 0 # 缁熻杩炵画闈欓煶鐨勬鏁�
- # speech_detected = False # 鏍囪鏄惁妫�娴嬪埌璇煶
- RECORD_NUM = 0
- global voices
- global speek
- speech_start, speech_end = False, False
- while True:
- while not voices.empty():
-
- data = voices.get()
- #print("闃熷垪鎺掗槦鏁�",voices.qsize())
- voices.task_done()
- buffer.append(data)
- if len(buffer) > 2:
- buffer.pop(0) # 濡傛灉缂撳瓨瓒呰繃涓や釜鐗囨锛屽垯鍒犻櫎鏈�鏃╃殑涓�涓�
-
- if speech_start:
- frames.append(data)
- RECORD_NUM += 1
- speech_start_i, speech_end_i = vad(data)
- # print(speech_start_i, speech_end_i)
- if speech_start_i:
- speech_start = speech_start_i
- # if not speech_detected:
- # print("妫�娴嬪埌浜哄０...")
- # speech_detected = True # 鏍囪涓烘娴嬪埌璇煶
- frames = []
- frames.extend(buffer) # 鎶婁箣鍓�2涓闊虫暟鎹揩鍔犲叆
- # silence_count = 0 # 閲嶇疆闈欓煶娆℃暟
- if speech_end_i or RECORD_NUM > 300:
- # silence_count += 1 # 澧炲姞闈欓煶娆℃暟
- # speech_end = speech_end_i
- speech_start = False
- # if RECORD_NUM > 300: #杩欓噷 50 鍙牴鎹渶姹傛敼涓哄悎閫傜殑鏁版嵁蹇暟閲�
- # print("璇磋瘽缁撴潫鎴栬�呰秴杩囪缃渶闀挎椂闂�...")
- audio_in = b"".join(frames)
- #asrt = threading.Thread(target=asr,args=(audio_in,))
- #asrt.start()
- speek.put(audio_in)
- #rec_result = inference_pipeline2(audio_in=audio_in) # ASR 妯″瀷閲岃窇涓�璺�
- frames = [] # 娓呯┖鎵�鏈夌殑甯ф暟鎹�
- buffer = [] # 娓呯┖缂撳瓨涓殑甯ф暟鎹紙鏈�澶氫袱涓墖娈碉級
- # silence_count = 0 # 缁熻杩炵画闈欓煶鐨勬鏁版竻闆�
- # speech_detected = False # 鏍囪鏄惁妫�娴嬪埌璇煶
- RECORD_NUM = 0
- time.sleep(0.01)
- time.sleep(0.01)
-
-
-
-s = threading.Thread(target=main)
-s.start()
-s = threading.Thread(target=asr)
-s.start()
-
+
+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()
\ No newline at end of file
--
Gitblit v1.9.1