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

update speaker infer

Browse Source
This commit is contained in:
shixian.shi 2024-01-22 16:22:49 +08:00
parent 3919d7454c
commit 9285e7d599
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
funasr/auto/auto_model.py
View File

@ -6,6 +6,7 @@ import random
import string
import logging
import os.path
import numpy as np
from tqdm import tqdm
from omegaconf import DictConfig, OmegaConf, ListConfig
@ -334,7 +335,7 @@ class AutoModel:
for _b in range(len(speech_j)):
vad_segments = [[sorted_data[beg_idx:end_idx][_b][0][0]/1000.0,
sorted_data[beg_idx:end_idx][_b][0][1]/1000.0,
speech_j[_b]]]
np.array(speech_j[_b])]]
segments = sv_chunk(vad_segments)
all_segments.extend(segments)
speech_b = [i[2] for i in segments]