mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-09-08 16:44:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

change the text normalization for upper_case_no_punc

Browse Source
This commit is contained in:
marcoyang1998 2023-09-08 09:57:24 +08:00
parent 77890a6115
commit 522273f97e
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
egs/libriheavy/ASR/zipformer_prompt_asr/text_normalization.py
View File

@ -30,7 +30,8 @@ def ref_text_normalization(ref_text: str) -> str:
def remove_non_alphabetic(text: str, strict: bool=True) -> str: def remove_non_alphabetic(text: str, strict: bool=True) -> str:
if not strict: if not strict:
# Note, this also keeps space, single quote(') and hypen (-) # Note, this also keeps space, single quote(') and hypen (-)
text = text.replace("--", " ") text = text.replace("-", " ")
text = text.replace("—", " ")
return re.sub("[^a-zA-Z0-9\s']+", "", text) return re.sub("[^a-zA-Z0-9\s']+", "", text)
else: else:
# only keeps space # only keeps space
@ -53,7 +54,7 @@ def upper_all_char(text: str) -> str:
return text.upper() return text.upper()
if __name__ == "__main__": if __name__ == "__main__":
ref_text = " Hello “! My name is ‘ haha" ref_text = "Mixed-case English transcription, with punctuation. Actually, it is fully not related."
print(ref_text) print(ref_text)
res = train_text_normalization(ref_text) res = upper_only_alpha(ref_text)
print(res) print(res)