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