From 4e44c9f46e550eab4ec6b70c099dcdae44eb9d61 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 23 三月 2023 20:34:21 +0800
Subject: [PATCH] Merge pull request #288 from alibaba-damo-academy/dev_gzf
---
funasr/runtime/python/websocket/ASR_server.py | 188 ++++++++++++++++++++++++++++++-----------------
1 files changed, 120 insertions(+), 68 deletions(-)
diff --git a/funasr/runtime/python/websocket/ASR_server.py b/funasr/runtime/python/websocket/ASR_server.py
index 3627d3a..9d0fd0b 100644
--- a/funasr/runtime/python/websocket/ASR_server.py
+++ b/funasr/runtime/python/websocket/ASR_server.py
@@ -1,4 +1,10 @@
-# 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�
+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
@@ -6,37 +12,80 @@
logger = get_logger(log_level=logging.CRITICAL)
logger.setLevel(logging.CRITICAL)
-import asyncio
-import websockets #鍖哄埆瀹㈡埛绔繖閲屾槸 websockets搴�
-import time
-from queue import Queue
-import threading
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument("--host",
+ type=str,
+ default="0.0.0.0",
+ required=False,
+ help="host ip, localhost, 0.0.0.0")
+parser.add_argument("--port",
+ type=int,
+ default=10095,
+ required=False,
+ help="grpc server port")
+parser.add_argument("--asr_model",
+ type=str,
+ default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
+ help="model from modelscope")
+parser.add_argument("--vad_model",
+ type=str,
+ default="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+ help="model from modelscope")
+
+parser.add_argument("--punc_model",
+ type=str,
+ default="damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727",
+ help="model from modelscope")
+parser.add_argument("--ngpu",
+ type=int,
+ default=1,
+ help="0 for cpu, 1 for gpu")
+
+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="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
- model_revision="v1.2.0",
+ model=args.vad_model,
+ model_revision=None,
output_dir=None,
batch_size=1,
+ mode='online',
+ ngpu=args.ngpu,
)
+param_dict_vad = {'in_cache': dict(), "is_final": False}
-# 鍒涘缓涓�涓狝SR瀵硅薄
-param_dict = dict()
-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(
+# 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_pipeline_asr = pipeline(
task=Tasks.auto_speech_recognition,
- model="damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404",
- param_dict=param_dict,
+ model=args.asr_model,
+ param_dict=param_dict_asr,
+ ngpu=args.ngpu,
)
+if args.punc_model is not None:
+ 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 echo(websocket, path):
+async def ws_serve(websocket, path):
global voices
try:
async for message in websocket:
@@ -47,28 +96,39 @@
except Exception as e:
print('Exception occurred:', e)
-start_server = websockets.serve(echo, "localhost", 8899, subprotocols=["binary"],ping_interval=None)
+start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None)
def vad(data): # 鎺ㄧ悊
- global vad_pipline
+ global vad_pipline, param_dict_vad
#print(type(data))
- segments_result = vad_pipline(audio_in=data)
- #print(segments_result)
- if len(segments_result) == 0:
- return False
- else:
- return True
+ # print(param_dict_vad)
+ segments_result = inference_pipeline_vad(audio_in=data, param_dict=param_dict_vad)
+ # print(segments_result)
+ # print(param_dict_vad)
+ speech_start = False
+ speech_end = False
+
+ if len(segments_result) == 0 or len(segments_result["text"]) > 1:
+ return speech_start, speech_end
+ if segments_result["text"][0][0] != -1:
+ speech_start = True
+ if segments_result["text"][0][1] != -1:
+ speech_end = True
+ return speech_start, speech_end
def asr(): # 鎺ㄧ悊
global inference_pipeline2
- global speek
+ global speek, param_dict_punc
while True:
while not speek.empty():
audio_in = speek.get()
speek.task_done()
- rec_result = inference_pipeline2(audio_in=audio_in)
- print(rec_result)
+ 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=param_dict_punc)
+ print(rec_result["text"])
time.sleep(0.1)
time.sleep(0.1)
@@ -76,11 +136,12 @@
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
+ # 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():
@@ -91,32 +152,35 @@
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_detected:
+ if speech_start:
frames.append(data)
- RECORD_NUM += 1
-
- if vad(data):
- 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
- else:
- silence_count += 1 # 澧炲姞闈欓煶娆℃暟
-
- if speech_detected and (silence_count > 4 or RECORD_NUM > 50): #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
+ 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)
@@ -128,16 +192,4 @@
s.start()
asyncio.get_event_loop().run_until_complete(start_server)
-asyncio.get_event_loop().run_forever()
-
-
-
-
-
-
-
-
-
-
-
-
+asyncio.get_event_loop().run_forever()
\ No newline at end of file
--
Gitblit v1.9.1