speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

vad begin point bias

Browse Source
This commit is contained in:
游雁 2023-05-08 00:41:21 +08:00
parent 5d165695e6
commit 24f2aa224a
2 changed files with 3 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
funasr/runtime/python/websocket/tmp/1best_recog/text
View File

@ -1,12 +1,2 @@
wav1 欢 迎 大
wav1 家 来
wav1 体 验 达
wav1 摩 院 推
wav1 出 的
wav1 语 音 识
wav1 别 模
wav1 型
wav2 欢 迎 大
wav2 家 来
wav2 体 验 达
wav2 摩 院 推
wav1 欢迎大家来体验达摩院推出的语音识别模型
wav2 。欢迎大家来体验达摩院推出的语音识别模型

1
funasr/runtime/python/websocket/ws_server_offline.py
View File

@ -96,6 +96,7 @@ async def ws_serve(websocket, path):
if not is_speaking:
websocket.vad_pre_idx = 0
frames = []
websocket.param_dict_vad = {'in_cache': dict()}
else:
frames = frames[-20:]