From 8dab6d184a034ca86eafa644ea0d2100aadfe27d Mon Sep 17 00:00:00 2001
From: jmwang66 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 09 五月 2023 10:58:33 +0800
Subject: [PATCH] Merge pull request #473 from alibaba-damo-academy/dev_smohan
---
funasr/runtime/python/websocket/ws_server_online.py | 29 +++++++++++++----------------
1 files changed, 13 insertions(+), 16 deletions(-)
diff --git a/funasr/runtime/python/websocket/ws_server_online.py b/funasr/runtime/python/websocket/ws_server_online.py
index a395d73..3c0fb16 100644
--- a/funasr/runtime/python/websocket/ws_server_online.py
+++ b/funasr/runtime/python/websocket/ws_server_online.py
@@ -12,7 +12,7 @@
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.utils.logger import get_logger
-from funasr_onnx.utils.frontend import load_bytes
+from funasr.runtime.python.onnxruntime.funasr_onnx.utils.frontend import load_bytes
tracemalloc.start()
@@ -28,6 +28,8 @@
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')
print("model loaded")
@@ -35,12 +37,10 @@
async def ws_serve(websocket, path):
- frames_online = []
+ frames_asr_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:
@@ -51,26 +51,26 @@
is_speaking = message["is_speaking"]
websocket.param_dict_asr_online["is_final"] = not is_speaking
-
+ websocket.wav_name = message.get("wav_name", "demo")
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)
+ frames_asr_online.append(audio)
+ if len(frames_asr_online) % message["chunk_interval"] == 0 or not is_speaking:
+ audio_in = b"".join(frames_asr_online)
await async_asr_online(websocket,audio_in)
- frames_online = []
+ frames_asr_online = []
except websockets.ConnectionClosed:
- print("ConnectionClosed...", websocket_users) # 閾炬帴鏂紑
+ print("ConnectionClosed...", websocket_users)
websocket_users.remove(websocket)
except websockets.InvalidState:
- print("InvalidState...") # 鏃犳晥鐘舵��
+ print("InvalidState...")
except Exception as e:
print("Exception:", e)
-async def async_asr_online(websocket,audio_in): # ASR鎺ㄧ悊
+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,
@@ -79,12 +79,9 @@
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"]})
+ message = json.dumps({"mode": "online", "text": rec_result["text"], "wav_name": websocket.wav_name})
await websocket.send(message)
-
start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None)
--
Gitblit v1.9.1