From e69e1c04b2e824ffda04ac2bdcb02db6e2fd75e2 Mon Sep 17 00:00:00 2001
From: Kinan Martin <kinanmartin0@gmail.com>
Date: Wed, 16 Apr 2025 07:15:25 +0900
Subject: [PATCH] separate transcript prep stage from bpe train stage

---
 egs/mls_english/ASR/prepare.sh | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/egs/mls_english/ASR/prepare.sh b/egs/mls_english/ASR/prepare.sh
index 27aaa5e37..eb42510b9 100644
--- a/egs/mls_english/ASR/prepare.sh
+++ b/egs/mls_english/ASR/prepare.sh
@@ -45,12 +45,15 @@ mkdir -p data/lang
 lang_dir=data/lang
 
 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
     log "Generating transcripts for BPE training"
     ./local/utils/generate_transcript.py --lang-dir $lang_dir
   fi
+fi
+
+if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then
+  log "Stage 2: Prepare BPE tokenizer"
 
   for vocab_size in ${vocab_sizes[@]}; do
     log "Training BPE model with vocab_size=${vocab_size}"