mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-08-08 09:32:20 +00:00
b25c234c51
* Minor fix to conformer-mmi * Minor fixes * Fix decode.py * add training files * train with ctc warmup * add pruned_transducer_stateless7_mmi * add zipformer_mmi/mmi_decode.py, using HP as decoding graph * add mmi_decode.py * remove pruned_transducer_stateless7_mmi * rename zipformer_mmi/train_with_ctc.py as zipformer_mmi/train.py * remove unused method * rename mmi_decode.py * add export.py pretrained.py jit_pretrained.py ... * add RESULTS.md * add CI test * add docs * add README.md Co-authored-by: pkufool <wkang.pku@gmail.com>
21 lines
535 B
Bash
Executable File
21 lines
535 B
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
lang_dir=data/lang_bpe_500
|
|
|
|
for ngram in 2 3 4 5; do
|
|
if [ ! -f $lang_dir/${ngram}gram.arpa ]; then
|
|
./shared/make_kn_lm.py \
|
|
-ngram-order ${ngram} \
|
|
-text $lang_dir/transcript_tokens.txt \
|
|
-lm $lang_dir/${ngram}gram.arpa
|
|
fi
|
|
|
|
if [ ! -f $lang_dir/${ngram}gram.fst.txt ]; then
|
|
python3 -m kaldilm \
|
|
--read-symbol-table="$lang_dir/tokens.txt" \
|
|
--disambig-symbol='#0' \
|
|
--max-order=${ngram} \
|
|
$lang_dir/${ngram}gram.arpa > $lang_dir/${ngram}gram.fst.txt
|
|
fi
|
|
done
|