mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-26 10:16:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update preprocess_commonvoice.py

Browse Source
This commit is contained in:
jinzr 2024-03-13 11:09:22 +08:00
parent b30a4d6162
commit eaceb691d8
1 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
egs/commonvoice/ASR/local/preprocess_commonvoice.py
View File

@ -21,7 +21,7 @@ import re
from pathlib import Path
from typing import Optional
from lhotse import CutSet, SupervisionSegment
from lhotse import CutSet
from lhotse.recipes.utils import read_manifests_if_cached
@ -82,6 +82,17 @@ def normalize_text(utt: str, language: str) -> str:
.replace("…", "")
.replace("⋯", "")
.replace("·", "")
.replace("﹒", "")
.replace("．", "")
.replace("：", "")
.replace("︰", "")
.replace("﹖", "")
.replace("（", "")
.replace("）", "")
.replace("－", "")
.replace("～", "")
.replace("；", "")
.replace("", "")
.upper()
)
else: