From b18f7d121f2f17df8bf2d0c2bbb223bc5ddbcc0f Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 25 五月 2023 16:11:22 +0800
Subject: [PATCH] docs

---
 funasr/runtime/python/websocket/ws_server_2pass.py |  104 ++++++++++++++++++++++++++++++++--------------------
 1 files changed, 64 insertions(+), 40 deletions(-)

diff --git a/funasr/runtime/python/websocket/ws_server_2pass.py b/funasr/runtime/python/websocket/ws_server_2pass.py
index ced67ff..df13ad9 100644
--- a/funasr/runtime/python/websocket/ws_server_2pass.py
+++ b/funasr/runtime/python/websocket/ws_server_2pass.py
@@ -5,7 +5,7 @@
 import logging
 import tracemalloc
 import numpy as np
-
+import ssl
 from parse_args import args
 from modelscope.pipelines import pipeline
 from modelscope.utils.constant import Tasks
@@ -46,7 +46,7 @@
     inference_pipeline_punc = pipeline(
         task=Tasks.punctuation,
         model=args.punc_model,
-        model_revision=None,
+        model_revision="v1.0.2",
         ngpu=args.ngpu,
         ncpu=args.ncpu,
     )
@@ -74,47 +74,58 @@
     websocket.param_dict_punc = {'cache': list()}
     websocket.vad_pre_idx = 0
     speech_start = False
+    speech_end_i = False
+    websocket.wav_name = "microphone"
+    print("new user connected", flush=True)
 
     try:
         async for message in websocket:
-            message = json.loads(message)
-            is_finished = message["is_finished"]
-            if not is_finished:
-                audio = bytes(message['audio'], 'ISO-8859-1')
-                frames.append(audio)
-                duration_ms = len(audio)//32
-                websocket.vad_pre_idx += duration_ms
-
-                is_speaking = message["is_speaking"]
-                websocket.param_dict_vad["is_final"] = not is_speaking
-                websocket.param_dict_asr_online["is_final"] = not is_speaking
-                websocket.param_dict_asr_online["chunk_size"] = message["chunk_size"]
-                websocket.wav_name = message.get("wav_name", "demo")
-                # asr online
-                frames_asr_online.append(audio)
-                if len(frames_asr_online) % message["chunk_interval"] == 0:
-                    audio_in = b"".join(frames_asr_online)
-                    await async_asr_online(websocket, audio_in)
-                    frames_asr_online = []
-                if speech_start:
-                    frames_asr.append(audio)
-                # vad online
-                speech_start_i, speech_end_i = await async_vad(websocket, audio)
-                if speech_start_i:
-                    speech_start = True
-                    beg_bias = (websocket.vad_pre_idx-speech_start_i)//duration_ms
-                    frames_pre = frames[-beg_bias:]
-                    frames_asr = []
-                    frames_asr.extend(frames_pre)
+            if isinstance(message, str):
+                messagejson = json.loads(message)
+        
+                if "is_speaking" in messagejson:
+                    websocket.is_speaking = messagejson["is_speaking"]
+                    websocket.param_dict_asr_online["is_final"] = not websocket.is_speaking
+                if "chunk_interval" in messagejson:
+                    websocket.chunk_interval = messagejson["chunk_interval"]
+                if "wav_name" in messagejson:
+                    websocket.wav_name = messagejson.get("wav_name")
+                if "chunk_size" in messagejson:
+                    websocket.param_dict_asr_online["chunk_size"] = messagejson["chunk_size"]
+            if len(frames_asr_online) > 0 or len(frames_asr) > 0 or not isinstance(message, str):
+                if not isinstance(message, str):
+                    frames.append(message)
+                    duration_ms = len(message)//32
+                    websocket.vad_pre_idx += duration_ms
+        
+                    # asr online
+                    frames_asr_online.append(message)
+                    websocket.param_dict_asr_online["is_final"] = speech_end_i
+                    if len(frames_asr_online) % websocket.chunk_interval == 0 or websocket.param_dict_asr_online["is_final"]:
+                        
+                        audio_in = b"".join(frames_asr_online)
+                        await async_asr_online(websocket, audio_in)
+                        frames_asr_online = []
+                    if speech_start:
+                        frames_asr.append(message)
+                    # vad online
+                    speech_start_i, speech_end_i = await async_vad(websocket, message)
+                    if speech_start_i:
+                        speech_start = True
+                        beg_bias = (websocket.vad_pre_idx-speech_start_i)//duration_ms
+                        frames_pre = frames[-beg_bias:]
+                        frames_asr = []
+                        frames_asr.extend(frames_pre)
                 # asr punc offline
-                if speech_end_i or not is_speaking:
+                if speech_end_i or not websocket.is_speaking:
+                    # print("vad end point")
                     audio_in = b"".join(frames_asr)
                     await async_asr(websocket, audio_in)
                     frames_asr = []
                     speech_start = False
-                    frames_asr_online = []
-                    websocket.param_dict_asr_online = {"cache": dict()}
-                    if not is_speaking:
+                    # frames_asr_online = []
+                    # websocket.param_dict_asr_online = {"cache": dict()}
+                    if not websocket.is_speaking:
                         websocket.vad_pre_idx = 0
                         frames = []
                         websocket.param_dict_vad = {'in_cache': dict()}
@@ -159,24 +170,37 @@
                     rec_result = inference_pipeline_punc(text_in=rec_result['text'],
                                                          param_dict=websocket.param_dict_punc)
                     # print("offline", rec_result)
-                message = json.dumps({"mode": "2pass-offline", "text": rec_result["text"], "wav_name": websocket.wav_name})
-                await websocket.send(message)
+                if 'text' in rec_result:
+                    message = json.dumps({"mode": "2pass-offline", "text": rec_result["text"], "wav_name": websocket.wav_name})
+                    await websocket.send(message)
 
 
 async def async_asr_online(websocket, audio_in):
     if len(audio_in) > 0:
         audio_in = load_bytes(audio_in)
+        # print(websocket.param_dict_asr_online.get("is_final", False))
         rec_result = inference_pipeline_asr_online(audio_in=audio_in,
                                                    param_dict=websocket.param_dict_asr_online)
-        if websocket.param_dict_asr_online["is_final"]:
-            websocket.param_dict_asr_online["cache"] = dict()
+        # print(rec_result)
+        if websocket.param_dict_asr_online.get("is_final", False):
+            return
+            #     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":
                 # print("online", rec_result)
                 message = json.dumps({"mode": "2pass-online", "text": rec_result["text"], "wav_name": websocket.wav_name})
                 await websocket.send(message)
 
+if len(args.certfile)>0:
+	ssl_context = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
+	
+	# Generate with Lets Encrypt, copied to this location, chown to current user and 400 permissions
+	ssl_cert = args.certfile
+	ssl_key = args.keyfile
 
-start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None)
+	ssl_context.load_cert_chain(ssl_cert, keyfile=ssl_key)
+	start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None,ssl=ssl_context)
+else:
+	start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None)
 asyncio.get_event_loop().run_until_complete(start_server)
 asyncio.get_event_loop().run_forever()
\ No newline at end of file

--
Gitblit v1.9.1