funasr sdk

funasr/runtime/docs/SDK_advanced_guide_offline.md

@@ -169,7 +169,7 @@ After completing the deployment of FunASR offline file transcription service on
 
 ### python-client
 ```shell
-python wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "./data/wav.scp" --send_without_sleep --output_dir "./results"
+python funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "./data/wav.scp" --send_without_sleep --output_dir "./results"
 ```
 
 Introduction to command parameters:

funasr/runtime/docs/SDK_advanced_guide_offline_zh.md

@@ -186,7 +186,7 @@ python -m funasr.export.export_model --model-name /path/to/finetune/speech_paraf
 
 ### python-client
 ```shell
-python wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "./data/wav.scp" --send_without_sleep --output_dir "./results"
+python funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "./data/wav.scp" --send_without_sleep --output_dir "./results"
 ```
 命令参数介绍：
 ```text

funasr/runtime/docs/SDK_tutorial.md

@@ -275,7 +275,7 @@ Requirement already satisfied: click>=8.0.4 in /usr/local/lib/python3.8/dist-pac
 Looking in indexes: http://mirrors.cloud.aliyuncs.com/pypi/simple/
 Requirement already satisfied: websockets in /usr/local/lib/python3.8/dist-packages (from -r /root/funasr_samples/python/requirements_client.txt (line 1)) (11.0.3)
 
-  Run python3 /root/funasr_samples/python/wss_client_asr.py --host 127.0.0.1 --port 10095 --mode offline --audio_in /root/funasr_samples/audio/asr_example.wav --send_without_sleep --output_dir ./funasr_samples/python
+  Run python3 /root/funasr_samples/python/funasr_wss_client.py --host 127.0.0.1 --port 10095 --mode offline --audio_in /root/funasr_samples/audio/asr_example.wav --send_without_sleep --output_dir ./funasr_samples/python
 
   ...
   ...
@@ -284,7 +284,7 @@ Requirement already satisfied: websockets in /usr/local/lib/python3.8/dist-packa
 Exception: sent 1000 (OK); then received 1000 (OK)
 end
 
-  If failed, you can try (python3 /root/funasr_samples/python/wss_client_asr.py --host 127.0.0.1 --port 10095 --mode offline --audio_in /root/funasr_samples/audio/asr_example.wav --send_without_sleep --output_dir ./funasr_samples/python) in your Shell.
+  If failed, you can try (python3 /root/funasr_samples/python/funasr_wss_client.py --host 127.0.0.1 --port 10095 --mode offline --audio_in /root/funasr_samples/audio/asr_example.wav --send_without_sleep --output_dir ./funasr_samples/python) in your Shell.
 
 ```
 
@@ -292,7 +292,7 @@ end
 
 If you want to directly run the client for testing, you can refer to the following simple instructions, taking the Python version as an example:
 ```shell
-python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --send_without_sleep --output_dir "./results"
+python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --send_without_sleep --output_dir "./results"
 ```
 
 Command parameter instructions: 

funasr/runtime/docs/SDK_tutorial_zh.md

@@ -37,7 +37,7 @@ sudo bash funasr-runtime-deploy-offline-cpu-zh.sh install --workspace /root/funa
 我们以Python语言客户端为例，进行说明，支持多种音频格式输入（.wav, .pcm, .mp3等），也支持视频输入(.mp4等)，以及多文件列表wav.scp输入，其他版本客户端请参考文档（[点击此处](#客户端用法详解)）
 
 ```shell
-python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --output_dir "./results"
+python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --output_dir "./results"
 ```
 
 ## 客户端用法详解
@@ -56,7 +56,7 @@ python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio
 若想直接运行client进行测试，可参考如下简易说明，以python版本为例：
 
 ```shell
-python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --output_dir "./results"
+python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --output_dir "./results"
 ```
 
 命令参数说明：

funasr/runtime/python/websocket/funasr_wss_client.py

@@ -8,7 +8,7 @@ import argparse
 import json
 import traceback
 from multiprocessing import Process
-from funasr.fileio.datadir_writer import DatadirWriter
+# from funasr.fileio.datadir_writer import DatadirWriter
 
 import logging
 
@@ -72,11 +72,13 @@ 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)
-    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():
@@ -186,6 +188,10 @@ async def message(id):
     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)), "w+", encoding="utf-8")
+    else:
+        ibest_writer = None
     try:
        while True:
         
@@ -193,13 +199,15 @@ async def message(id):
             meg = json.loads(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)
@@ -216,7 +224,7 @@ async def message(id):
                     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 +235,6 @@ async def message(id):
  
 
 
-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:

funasr/runtime/python/websocket/funasr_wss_server.py

@@ -243,7 +243,7 @@ async def async_asr(websocket, audio_in):
                                                          param_dict=websocket.param_dict_punc)
                     # print("offline", rec_result)
                 if 'text' in rec_result:
-                    message = json.dumps({"mode": "2pass-offline", "text": rec_result["text"], "wav_name": websocket.wav_name})
+                    message = json.dumps({"mode": websocket.mode, "text": rec_result["text"], "wav_name": websocket.wav_name})
                     await websocket.send(message)
 
 
@@ -260,7 +260,7 @@ async def async_asr_online(websocket, audio_in):
         if "text" in rec_result:
             if rec_result["text"] != "sil" and rec_result["text"] != "waiting_for_more_voice":
                 # print("online", rec_result)
-                message = json.dumps({"mode": "2pass-online", "text": rec_result["text"], "wav_name": websocket.wav_name})
+                message = json.dumps({"mode": websocket.mode, "text": rec_result["text"], "wav_name": websocket.wav_name})
                 await websocket.send(message)
 
 if len(args.certfile)>0: