From 4ae9a00ec5fcf79c67796ede12bf5087b1d403f1 Mon Sep 17 00:00:00 2001 From: yfyeung Date: Tue, 2 Apr 2024 07:52:11 +0000 Subject: [PATCH] update --- egs/gigaspeech2/SSL/local/preprocess_gigaspeech2.py | 4 ++-- egs/gigaspeech2/SSL/prepare.sh | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/egs/gigaspeech2/SSL/local/preprocess_gigaspeech2.py b/egs/gigaspeech2/SSL/local/preprocess_gigaspeech2.py index 2989157c0..8647a7594 100755 --- a/egs/gigaspeech2/SSL/local/preprocess_gigaspeech2.py +++ b/egs/gigaspeech2/SSL/local/preprocess_gigaspeech2.py @@ -17,8 +17,8 @@ import logging import re -from pathlib import Path import unicodedata +from pathlib import Path from lhotse import CutSet, SupervisionSegment 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\u0046", "องศาฟาเรนไฮต์", text) # °F text = re.sub(r"\u00B0", "องศา", text) # ° - + # Remove blank symbols text = re.sub(r"\s", "", text) diff --git a/egs/gigaspeech2/SSL/prepare.sh b/egs/gigaspeech2/SSL/prepare.sh index 210441d3f..f20f57f85 100755 --- a/egs/gigaspeech2/SSL/prepare.sh +++ b/egs/gigaspeech2/SSL/prepare.sh @@ -48,7 +48,7 @@ if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then log "Stage 2: Compute fbank for gigaspeech2" mkdir -p data/fbank if [ ! -e data/fbank/.gigaspeech2.done ]; then - ./local/compute_fbank_gigaspeech2.py + ./local/compute_fbank_gigaspeech2.py --lang $lang touch data/fbank/.gigaspeech2.done fi fi