From fa2f52caeaf6ad4b7624f53d4d9207b89edea5a6 Mon Sep 17 00:00:00 2001
From: Yabin Li <wucong.lyb@alibaba-inc.com>
Date: 星期三, 05 七月 2023 10:21:38 +0800
Subject: [PATCH] Update SDK_advanced_guide_offline_zh.md

---
 funasr/runtime/python/websocket/wss_client_asr.py |   65 +++++++++++++++++++++++---------
 1 files changed, 46 insertions(+), 19 deletions(-)

diff --git a/funasr/runtime/python/websocket/wss_client_asr.py b/funasr/runtime/python/websocket/wss_client_asr.py
index bd9e89f..dcd9576 100644
--- a/funasr/runtime/python/websocket/wss_client_asr.py
+++ b/funasr/runtime/python/websocket/wss_client_asr.py
@@ -40,12 +40,12 @@
                     help="audio_in")
 parser.add_argument("--send_without_sleep",
                     action="store_true",
-                    default=False,
+                    default=True,
                     help="if audio_in is set, send_without_sleep")
-parser.add_argument("--test_thread_num",
+parser.add_argument("--thread_num",
                     type=int,
                     default=1,
-                    help="test_thread_num")
+                    help="thread_num")
 parser.add_argument("--words_max_print",
                     type=int,
                     default=10000,
@@ -71,6 +71,8 @@
 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)
@@ -158,22 +160,45 @@
                 message = json.dumps({"is_speaking": is_speaking})
                 #voices.put(message)
                 await websocket.send(message)
-            # print("data_chunk: ", len(data_chunk))
-            # print(voices.qsize())
-            sleep_duration = 0.001 if args.send_without_sleep else 60 * args.chunk_size[1] / args.chunk_interval / 1000
+ 
+            sleep_duration = 0.001 if args.mode == "offline" else 60 * args.chunk_size[1] / args.chunk_interval / 1000
+            
             await asyncio.sleep(sleep_duration)
+    # when all data sent, we need to close websocket
     while not voices.empty():
          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 ws_send():
+    global voices
+    global websocket
+    print("started to sending data!")
+    while True:
+        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)
 
  
              
 async def message(id):
-    global websocket,voices
+    global websocket,voices,offline_msg_done
     text_print = ""
     text_print_2pass_online = ""
     text_print_2pass_offline = ""
@@ -183,7 +208,6 @@
             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
@@ -198,6 +222,7 @@
                 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)
@@ -233,8 +258,10 @@
   if args.audio_in is None:
        chunk_begin=0
        chunk_size=1
-  global websocket,voices
+  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()
@@ -250,9 +277,9 @@
             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, task3)
+        task2 = asyncio.create_task(ws_send())
+        task3 = asyncio.create_task(message(str(id)+"_"+str(i))) #processid+fileid
+        await asyncio.gather(task, task2, task3)
   exit(0)
     
 
@@ -284,16 +311,16 @@
                     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)
-            remain_wavs = total_len - chunk_size * args.test_thread_num
+        if total_len >= args.thread_num:
+            chunk_size = int(total_len / args.thread_num)
+            remain_wavs = total_len - chunk_size * args.thread_num
         else:
             chunk_size = 1
             remain_wavs = 0
 
         process_list = []
         chunk_begin = 0
-        for i in range(args.test_thread_num):
+        for i in range(args.thread_num):
             now_chunk_size = chunk_size
             if remain_wavs > 0:
                 now_chunk_size = chunk_size + 1

--
Gitblit v1.9.1