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

bug fix for libtorch tp

Browse Source
This commit is contained in:
shixian.shi 2023-10-19 15:45:16 +08:00
parent 76efe7a09e
commit 3be08cbc2f
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
funasr/runtime/python/libtorch/funasr_torch/utils/timestamp_utils.py
View File

@ -3,7 +3,7 @@ import numpy as np
def time_stamp_lfr6_onnx(us_cif_peak, char_list, begin_time=0.0, total_offset=-1.5): def time_stamp_lfr6_onnx(us_cif_peak, char_list, begin_time=0.0, total_offset=-1.5):
if not len(char_list): if not len(char_list):
return [] return '', []
START_END_THRESHOLD = 5 START_END_THRESHOLD = 5
MAX_TOKEN_DURATION = 30 MAX_TOKEN_DURATION = 30
TIME_RATE = 10.0 * 6 / 1000 / 3 # 3 times upsampled TIME_RATE = 10.0 * 6 / 1000 / 3 # 3 times upsampled