From 7557fa87a8043867e39f4920b38d6163d54095ef Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 08 五月 2023 00:13:59 +0800
Subject: [PATCH] Merge pull request #468 from alibaba-damo-academy/dev_websocket_offline

---
 funasr/version.txt                                   |    2 +-
 funasr/runtime/python/websocket/ws_server_offline.py |    6 ++++--
 funasr/runtime/python/websocket/README.md            |    4 ++--
 funasr/runtime/python/websocket/ws_client.py         |   23 ++++++++++++++++++++---
 funasr/runtime/python/websocket/ws_server_online.py  |    8 ++++----
 5 files changed, 31 insertions(+), 12 deletions(-)

diff --git a/funasr/runtime/python/websocket/README.md b/funasr/runtime/python/websocket/README.md
index 76405ea..473c37a 100644
--- a/funasr/runtime/python/websocket/README.md
+++ b/funasr/runtime/python/websocket/README.md
@@ -58,7 +58,7 @@
 ##### Loadding from wav.scp(kaldi style)
 ```shell
 # --chunk_interval, "10": 600/10=60ms, "5"=600/5=120ms, "20": 600/12=30ms
-python ws_client.py --host "0.0.0.0" --port 10095 --chunk_interval 10 --words_max_print 100 --audio_in "./data/wav.scp" --send_without_sleep
+python ws_client.py --host "0.0.0.0" --port 10095 --chunk_interval 10 --words_max_print 100 --audio_in "./data/wav.scp" --send_without_sleep --output_dir "./results"
 ```
 #### ASR streaming client
 ##### Recording from mircrophone
@@ -69,7 +69,7 @@
 ##### Loadding from wav.scp(kaldi style)
 ```shell
 # --chunk_size, "5,10,5"=600ms, "8,8,4"=480ms
-python ws_client.py --host "0.0.0.0" --port 10095 --chunk_size "5,10,5" --audio_in "./data/wav.scp" --words_max_print 100
+python ws_client.py --host "0.0.0.0" --port 10095 --chunk_size "5,10,5" --audio_in "./data/wav.scp" --words_max_print 100 --output_dir "./results"
 ```
 
 #### ASR offline/online 2pass client
diff --git a/funasr/runtime/python/websocket/ws_client.py b/funasr/runtime/python/websocket/ws_client.py
index d8bbb65..bbc49b1 100644
--- a/funasr/runtime/python/websocket/ws_client.py
+++ b/funasr/runtime/python/websocket/ws_client.py
@@ -7,7 +7,9 @@
 import argparse
 import json
 import traceback
-from multiprocessing import  Process
+from multiprocessing import Process
+from funasr.fileio.datadir_writer import DatadirWriter
+
 parser = argparse.ArgumentParser()
 parser.add_argument("--host",
                     type=str,
@@ -43,6 +45,10 @@
                     type=int,
                     default=100,
                     help="chunk")
+parser.add_argument("--output_dir",
+                    type=str,
+                    default=None,
+                    help="output_dir")
 
 args = parser.parse_args()
 args.chunk_size = [int(x) for x in args.chunk_size.split(",")]
@@ -50,6 +56,11 @@
 # voices = asyncio.Queue()
 from queue import Queue
 voices = Queue()
+
+ibest_writer = None
+if args.output_dir is not None:
+    writer = DatadirWriter(args.output_dir)
+    ibest_writer = writer[f"1best_recog"]
 
 async def record_microphone():
     is_finished = False
@@ -91,7 +102,9 @@
         wavs = [args.audio_in]
     for wav in wavs:
         wav_splits = wav.strip().split()
+        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]
+        
         # bytes_f = open(wav_path, "rb")
         # bytes_data = bytes_f.read()
         with wave.open(wav_path, "rb") as wav_file:
@@ -112,7 +125,7 @@
             beg = i*stride
             data = audio_bytes[beg:beg+stride]
             data = data.decode('ISO-8859-1')
-            message = json.dumps({"chunk_size": args.chunk_size, "chunk_interval": args.chunk_interval, "is_speaking": is_speaking, "audio": data, "is_finished": is_finished})
+            message = json.dumps({"chunk_size": args.chunk_size, "chunk_interval": args.chunk_interval, "is_speaking": is_speaking, "audio": data, "is_finished": is_finished, "wav_name": wav_name})
             voices.put(message)
             # print("data_chunk: ", len(data_chunk))
             # print(voices.qsize())
@@ -152,14 +165,18 @@
             # print(meg, end = '')
             # print("\r")
             # print(meg)
+            wav_name = meg.get("wav_name", "demo")
+            print(wav_name)
             text = meg["text"][0]
+            if ibest_writer is not None:
+                ibest_writer["text"][wav_name] = text
             if meg["mode"] == "online":
                 text_print += " {}".format(text)
             else:
                 text_print += "{}".format(text)
             text_print = text_print[-args.words_max_print:]
             os.system('clear')
-            print("\r"+str(id)+":"+text_print)
+            print("\rpid"+str(id)+": "+text_print)
         except Exception as e:
             print("Exception:", e)
             traceback.print_exc()
diff --git a/funasr/runtime/python/websocket/ws_server_offline.py b/funasr/runtime/python/websocket/ws_server_offline.py
index 7873918..c60ea6f 100644
--- a/funasr/runtime/python/websocket/ws_server_offline.py
+++ b/funasr/runtime/python/websocket/ws_server_offline.py
@@ -78,6 +78,7 @@
 
                 is_speaking = message["is_speaking"]
                 websocket.param_dict_vad["is_final"] = not is_speaking
+                websocket.wav_name = message.get("wav_name", "demo")
                 if speech_start:
                     frames_asr.append(audio)
                 speech_start_i, speech_end_i = await async_vad(websocket, audio)
@@ -136,8 +137,9 @@
                     rec_result = inference_pipeline_punc(text_in=rec_result['text'],
                                                          param_dict=websocket.param_dict_punc)
                     # print(rec_result)
-                    message = json.dumps({"mode": "offline", "text": [rec_result["text"]]})
-                    await websocket.send(message)
+                message = json.dumps({"mode": "offline", "text": [rec_result["text"]], "wav_name": websocket.wav_name})
+                await websocket.send(message)
+                
                     
  
 
diff --git a/funasr/runtime/python/websocket/ws_server_online.py b/funasr/runtime/python/websocket/ws_server_online.py
index 6ea8f39..b1cd4ea 100644
--- a/funasr/runtime/python/websocket/ws_server_online.py
+++ b/funasr/runtime/python/websocket/ws_server_online.py
@@ -53,7 +53,7 @@
 
                 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)
@@ -81,9 +81,9 @@
                     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"]})
+                        # if len(rec_result["text"])>0:
+                        #     rec_result["text"][0]=rec_result["text"][0] #.replace(" ","")
+                        message = json.dumps({"mode": "online", "text": rec_result["text"], "wav_name": websocket.wav_name})
                         await websocket.send(message)
 
 
diff --git a/funasr/version.txt b/funasr/version.txt
index 0bfccb0..ef52a64 100644
--- a/funasr/version.txt
+++ b/funasr/version.txt
@@ -1 +1 @@
-0.4.5
+0.4.6

--
Gitblit v1.9.1