mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-08 09:32:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix gigaspeech_prepare.sh (#1734)

Browse Source
This commit is contained in:
Yifan Yang 2024-08-28 12:15:01 +08:00 committed by GitHub
parent a6c02a4d8c
commit cea0dbe7b1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
egs/gigaspeech/ASR/prepare.sh
View File

@ -161,14 +161,14 @@ if [ $stage -le 5 ] && [ $stop_stage -ge 5 ]; then
log "Stage 5: Split XL subset into pieces (may take 30 minutes)"
split_dir=data/fbank/XL_split
if [ ! -f $split_dir/.split_completed ]; then
lhotse split-lazy ./data/fbank/cuts_XL_raw.jsonl.gz $split_dir $num_per_split
lhotse split-lazy ./data/fbank/gigaspeech_cuts_XL_raw.jsonl.gz $split_dir $num_per_split
touch $split_dir/.split_completed
fi
fi
if [ $stage -le 6 ] && [ $stop_stage -ge 6 ]; then
log "Stage 6: Compute features for XL"
num_splits=$(find data/fbank/XL_split -name "cuts_XL_raw.*.jsonl.gz" | wc -l)
num_splits=$(find data/fbank/XL_split -name "gigaspeech_cuts_XL_raw.*.jsonl.gz" | wc -l)
python3 ./local/compute_fbank_gigaspeech_splits.py \
--num-workers 20 \
--batch-duration 600 \
@ -177,9 +177,9 @@ fi
if [ $stage -le 7 ] && [ $stop_stage -ge 7 ]; then
log "Stage 7: Combine features for XL (may take 3 hours)"
if [ ! -f data/fbank/cuts_XL.jsonl.gz ]; then
pieces=$(find data/fbank/XL_split -name "cuts_XL.*.jsonl.gz")
lhotse combine $pieces data/fbank/cuts_XL.jsonl.gz
if [ ! -f data/fbank/gigaspeech_cuts_XL.jsonl.gz ]; then
pieces=$(find data/fbank/XL_split -name "gigaspeech_cuts_XL.*.jsonl.gz")
lhotse combine $pieces data/fbank/gigaspeech_cuts_XL.jsonl.gz
fi
fi