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

Update preprocess_kespeech.py

Browse Source
This commit is contained in:
zr_jin 2023-09-02 17:50:09 +08:00
parent 40a7c17a3c
commit ecffd6ce93
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
egs/multi_zh-hans/ASR/local/preprocess_kespeech.py
View File

@ -78,6 +78,8 @@ def preprocess_kespeech(speed_perturb: bool = False):
list(manifests.keys()), list(manifests.keys()),
dataset_parts, dataset_parts,
) )
logging_threshold = 50
logging_count = 0
for partition, m in manifests.items(): for partition, m in manifests.items():
logging.info(f"Processing {partition}") logging.info(f"Processing {partition}")
@ -97,7 +99,8 @@ def preprocess_kespeech(speed_perturb: bool = False):
orig_text = text orig_text = text
sup.text = normalize_text(sup.text) sup.text = normalize_text(sup.text)
text = str(sup.text) text = str(sup.text)
if len(orig_text) != len(text): if len(orig_text) != len(text) and logging_count < logging_threshold:
logging_count += 1
logging.info( logging.info(
f"\nOriginal text vs normalized text:\n{orig_text}\n{text}" f"\nOriginal text vs normalized text:\n{orig_text}\n{text}"
) )