Skip to content

Get text in tedlium r3 rnnlm training script #3039

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
danpovey merged 1 commit into from
Feb 18, 2019
Merged

Get text in tedlium r3 rnnlm training script #3039

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions egs/tedlium/s5_r3/local/rnnlm/tuning/run_lstm_tdnn_a.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,6 @@ epochs=20
[ -z "$cmd" ] && cmd=$train_cmd

text_from_audio=data/train/text
text=data/LM/train.txt
wordlist=data/lang_chain/words.txt
dev_sents=10000
text_dir=data/rnnlm/text
Expand All @@ -44,8 +43,9 @@ done

if [ $stage -le 0 ]; then
mkdir -p $text_dir
gunzip -c db/TEDLIUM_release-3/LM/*.en.gz | sed 's/ <\/s>//g' > $text_dir/train.txt
# shuffle text from audio and lm
cat $text_from_audio | cut -d ' ' -f2- | cat $text |\
cat $text_from_audio | cut -d ' ' -f2- | cat $text_dir/train.txt |\
shuf > data/rnnlm/full_lm_data.shuffled
# create dev and train sets based on audio and LM data
cat data/rnnlm/full_lm_data.shuffled | head -n $dev_sents> $text_dir/dev.txt
Expand Down