mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-12-11 06:55:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

limit normalize log

Browse Source
This commit is contained in:
Yifan Yang 2023-05-31 12:07:45 +08:00
parent 787a461dfc
commit 44cb7c7967
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
egs/peoples_speech/ASR/local/preprocess_peoples_speech.py
View File

@ -85,15 +85,17 @@ def preprocess_peoples_speech(dataset: Optional[str] = None):
continue
logging.info(f"Normalizing text in {partition}")
i = 0
for sup in m["supervisions"]:
text = str(sup.text)
orig_text = text
sup.text = normalize_text(sup.text)
text = str(sup.text)
if len(orig_text) != len(text):
if i < 10 and len(orig_text) != len(text):
logging.info(
f"\nOriginal text vs normalized text:\n{orig_text}\n{text}"
)
i += 1
# Create long-recording cut manifests.
cut_set = CutSet.from_manifests(