mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-26 18:24:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
yfyeung 2024-04-02 07:52:11 +00:00
parent f5b8d5dad2
commit 4ae9a00ec5
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
egs/gigaspeech2/SSL/local/preprocess_gigaspeech2.py
View File

@ -17,8 +17,8 @@
import logging import logging
import re import re
from pathlib import Path
import unicodedata import unicodedata
from pathlib import Path
from lhotse import CutSet, SupervisionSegment from lhotse import CutSet, SupervisionSegment
from lhotse.recipes.utils import read_manifests_if_cached from lhotse.recipes.utils import read_manifests_if_cached
@ -73,7 +73,7 @@ def normalize_text(
text = re.sub(r"\u00B0\u0043", "องศาเซลเซียส", text) # °C text = re.sub(r"\u00B0\u0043", "องศาเซลเซียส", text) # °C
text = re.sub(r"\u00B0\u0046", "องศาฟาเรนไฮต์", text) # °F text = re.sub(r"\u00B0\u0046", "องศาฟาเรนไฮต์", text) # °F
text = re.sub(r"\u00B0", "องศา", text) # ° text = re.sub(r"\u00B0", "องศา", text) # °
# Remove blank symbols # Remove blank symbols
text = re.sub(r"\s", "", text) text = re.sub(r"\s", "", text)

2
egs/gigaspeech2/SSL/prepare.sh
View File

@ -48,7 +48,7 @@ if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then
log "Stage 2: Compute fbank for gigaspeech2" log "Stage 2: Compute fbank for gigaspeech2"
mkdir -p data/fbank mkdir -p data/fbank
if [ ! -e data/fbank/.gigaspeech2.done ]; then if [ ! -e data/fbank/.gigaspeech2.done ]; then
./local/compute_fbank_gigaspeech2.py ./local/compute_fbank_gigaspeech2.py --lang $lang
touch data/fbank/.gigaspeech2.done touch data/fbank/.gigaspeech2.done
fi fi
fi fi