chrissewell/whisperX
1
0
Fork 0
mirror of https://github.com/m-bain/whisperX.git synced 2025-07-01 18:17:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

refactor: add type hints

Browse Source
This commit is contained in:
Barabazs
2025-01-05 11:26:18 +01:00
parent 0f7f9f9f83
commit 9a8967f27e
6 changed files with 111 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
whisperx/conjunctions.py
View File

@ -1,5 +1,8 @@
# conjunctions.py
from typing import Set
conjunctions_by_language = {
'en': {'and', 'whether', 'or', 'as', 'but', 'so', 'for', 'nor', 'which', 'yet', 'although', 'since', 'unless', 'when', 'while', 'because', 'if', 'how', 'that', 'than', 'who', 'where', 'what', 'near', 'before', 'after', 'across', 'through', 'until', 'once', 'whereas', 'even', 'both', 'either', 'neither', 'though'},
'fr': {'et', 'ou', 'mais', 'parce', 'bien', 'pendant', 'quand', 'où', 'comme', 'si', 'que', 'avant', 'après', 'aussitôt', 'jusqu’à', 'à', 'malgré', 'donc', 'tant', 'puisque', 'ni', 'soit', 'bien', 'encore', 'dès', 'lorsque'},
@ -36,8 +39,9 @@ commas_by_language = {
'ur': '،'
}
def get_conjunctions(lang_code):
def get_conjunctions(lang_code: str) -> Set[str]:
return conjunctions_by_language.get(lang_code, set())
def get_comma(lang_code):
return commas_by_language.get(lang_code, ',')
def get_comma(lang_code: str) -> str:
return commas_by_language.get(lang_code, ",")