mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-26 18:24:18 +00:00
Update preprocess_mdcc.py
This commit is contained in:
parent
27c9a90dc6
commit
123cd9cb6d
@ -118,7 +118,7 @@ def get_word_segments(lines: List[str]) -> List[str]:
|
|||||||
def get_words(lines: List[str]) -> List[str]:
|
def get_words(lines: List[str]) -> List[str]:
|
||||||
words = set()
|
words = set()
|
||||||
for line in tqdm(lines, desc="Getting words"):
|
for line in tqdm(lines, desc="Getting words"):
|
||||||
words.update(line.strip().split(" "))
|
words.update(line.replace("\n", "").split(" "))
|
||||||
return list(words)
|
return list(words)
|
||||||
|
|
||||||
|
|
||||||
|
Loading…
x
Reference in New Issue
Block a user