From c2e4e3c2e9be855277d9f4fa9cd0544892ff829a Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 30 八月 2023 09:57:30 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add

---
 funasr/runtime/python/websocket/funasr_wss_client.py |   73 ++++++++++++++++++++----------------
 1 files changed, 40 insertions(+), 33 deletions(-)

diff --git a/funasr/runtime/python/websocket/funasr_wss_client.py b/funasr/runtime/python/websocket/funasr_wss_client.py
index fc4d516..bed0081 100644
--- a/funasr/runtime/python/websocket/funasr_wss_client.py
+++ b/funasr/runtime/python/websocket/funasr_wss_client.py
@@ -8,11 +8,10 @@
 import json
 import traceback
 from multiprocessing import Process
-from funasr.fileio.datadir_writer import DatadirWriter
+# from funasr.fileio.datadir_writer import DatadirWriter
 
 import logging
 
-SUPPORT_AUDIO_TYPE_SETS = ['.wav', '.pcm']
 logging.basicConfig(level=logging.ERROR)
 
 parser = argparse.ArgumentParser()
@@ -72,11 +71,13 @@
 
 voices = Queue()
 offline_msg_done=False
- 
-ibest_writer = None
+
 if args.output_dir is not None:
-    writer = DatadirWriter(args.output_dir)
-    ibest_writer = writer[f"1best_recog"]
+    # if os.path.exists(args.output_dir):
+    #     os.remove(args.output_dir)
+        
+    if not os.path.exists(args.output_dir):
+        os.makedirs(args.output_dir)
 
 
 async def record_microphone():
@@ -136,8 +137,17 @@
                 frames = wav_file.readframes(wav_file.getnframes())
                 audio_bytes = bytes(frames)
         else:
-            raise NotImplementedError(
-                f'Not supported audio type')
+            import ffmpeg
+            try:
+                # This launches a subprocess to decode audio while down-mixing and resampling as necessary.
+                # Requires the ffmpeg CLI and `ffmpeg-python` package to be installed.
+                audio_bytes, _ = (
+                    ffmpeg.input(wav_path, threads=0)
+                    .output("-", format="s16le", acodec="pcm_s16le", ac=1, ar=16000)
+                    .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
+                )
+            except ffmpeg.Error as e:
+                raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e
 
         # stride = int(args.chunk_size/1000*16000*2)
         stride = int(60 * args.chunk_size[1] / args.chunk_interval / 1000 * 16000 * 2)
@@ -166,10 +176,9 @@
             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)
+    
+    if not args.mode=="offline":
+        await asyncio.sleep(2)
     # offline model need to wait for message recved
     
     if args.mode=="offline":
@@ -186,27 +195,38 @@
     text_print = ""
     text_print_2pass_online = ""
     text_print_2pass_offline = ""
+    if args.output_dir is not None:
+        ibest_writer = open(os.path.join(args.output_dir, "text.{}".format(id)), "a", encoding="utf-8")
+    else:
+        ibest_writer = None
     try:
        while True:
         
             meg = await websocket.recv()
             meg = json.loads(meg)
+            # print(meg)
             wav_name = meg.get("wav_name", "demo")
             text = meg["text"]
-            if ibest_writer is not None:
-                ibest_writer["text"][wav_name] = text
 
+            if ibest_writer is not None:
+                text_write_line = "{}\t{}\n".format(wav_name, text)
+                ibest_writer.write(text_write_line)
+                
             if meg["mode"] == "online":
                 text_print += "{}".format(text)
                 text_print = text_print[-args.words_max_print:]
-                # os.system('clear')
+                os.system('clear')
                 print("\rpid" + str(id) + ": " + text_print)
             elif meg["mode"] == "offline":
                 text_print += "{}".format(text)
-                text_print = text_print[-args.words_max_print:]
+                # text_print = text_print[-args.words_max_print:]
                 # os.system('clear')
-                print("\rpid" + str(id) + ": " + text_print)
-                offline_msg_done=True
+                print("\rpid" + str(id) + ": " + wav_name + ": " + text_print)
+                if ("is_final" in meg and meg["is_final"]==False):
+                    offline_msg_done = True
+                
+                if not "is_final" in meg:
+                    offline_msg_done = True
             else:
                 if meg["mode"] == "2pass-online":
                     text_print_2pass_online += "{}".format(text)
@@ -216,7 +236,7 @@
                     text_print = text_print_2pass_offline + "{}".format(text)
                     text_print_2pass_offline += "{}".format(text)
                 text_print = text_print[-args.words_max_print:]
-                # os.system('clear')
+                os.system('clear')
                 print("\rpid" + str(id) + ": " + text_print)
                 offline_msg_done=True
 
@@ -227,17 +247,6 @@
  
 
 
-async def print_messge():
-    global websocket
-    while True:
-        try:
-            meg = await websocket.recv()
-            meg = json.loads(meg)
-            print(meg)
-        except Exception as e:
-            print("Exception:", e)
-            #traceback.print_exc()
-            exit(0)
 
 async def ws_client(id, chunk_begin, chunk_size):
   if args.audio_in is None:
@@ -290,9 +299,7 @@
             wav_name = wav_splits[0] if len(wav_splits) > 1 else "demo"
             wav_path = wav_splits[1] if len(wav_splits) > 1 else wav_splits[0]
             audio_type = os.path.splitext(wav_path)[-1].lower()
-            if audio_type not in SUPPORT_AUDIO_TYPE_SETS:
-                raise NotImplementedError(
-                    f'Not supported audio type: {audio_type}')
+
 
         total_len = len(wavs)
         if total_len >= args.thread_num:

--
Gitblit v1.9.1