mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-09 10:02:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

separate transcript prep stage from bpe train stage

Browse Source
This commit is contained in:
Kinan Martin 2025-04-16 07:15:25 +09:00
parent 6e81d9aa5b
commit e69e1c04b2
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
egs/mls_english/ASR/prepare.sh
View File

@ -45,12 +45,15 @@ mkdir -p data/lang
lang_dir=data/lang lang_dir=data/lang
if [ $stage -le 1 ] && [ $stop_stage -ge 1 ]; then if [ $stage -le 1 ] && [ $stop_stage -ge 1 ]; then
log "Stage 1: Prepare BPE tokenizer" log "Stage 1: Prepare transcript for BPE training"
if [ ! -f $lang_dir/transcript.txt ]; then if [ ! -f $lang_dir/transcript.txt ]; then
log "Generating transcripts for BPE training" log "Generating transcripts for BPE training"
./local/utils/generate_transcript.py --lang-dir $lang_dir ./local/utils/generate_transcript.py --lang-dir $lang_dir
fi fi
fi
if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then
log "Stage 2: Prepare BPE tokenizer"
for vocab_size in ${vocab_sizes[@]}; do for vocab_size in ${vocab_sizes[@]}; do
log "Training BPE model with vocab_size=${vocab_size}" log "Training BPE model with vocab_size=${vocab_size}"