Commit 0474456a authored by Abdelwahab HEBA's avatar Abdelwahab HEBA
Browse files

remove sil token

parent f9349a6c
...@@ -54,8 +54,8 @@ def transformation_text(text): ...@@ -54,8 +54,8 @@ def transformation_text(text):
text=re.sub(r":|\?|/|\!|<|>|#+","",text) text=re.sub(r":|\?|/|\!|<|>|#+","",text)
# replace silence character with <sil> : OK # replace silence character with <sil> : OK
#text=re.sub(r"(\+)", "<sil>", text) #text=re.sub(r"(\+)", "<sil>", text)
text=re.sub(r"(\+)", "!SIL", text) text=re.sub(r"(\+)", "", text)
text=re.sub(r"(///)", "!SIL", text) text=re.sub(r"(///)", "", text)
#text=re.sub(r"(///)", "<long-sil>", text) #text=re.sub(r"(///)", "<long-sil>", text)
if len(re.findall(r"/.+/", text)) > 0: if len(re.findall(r"/.+/", text)) > 0:
#print "AVANT***********"+text #print "AVANT***********"+text
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment