mirror of
https://github.com/facebookresearch/fairseq.git
synced 2024-09-11 09:15:43 +03:00
Update prepare_audio_v2.sh
Fix a bug that dumping the km labels without actually learning the kmeans.
This commit is contained in:
parent
0c5731f921
commit
d29a12fc9b
@ -63,6 +63,7 @@ mkdir -p $tgt_dir/mfcc
|
||||
# Consider spliting corpus into chuncks for large corpus, see HuBERT preprocessing for more details
|
||||
python $FAIRSEQ_ROOT/examples/hubert/simple_kmeans/dump_mfcc_feature.py \
|
||||
$tgt_dir $train_split 1 0 $tgt_dir/mfcc
|
||||
python $FAIRSEQ_ROOT/examples/hubert/simple_kmeans/learn_kmeans.py ${tgt_dir}/mfcc ${train_split} 1 ${tgt_dir}/mfcc/cls${dim} ${dim}
|
||||
python $FAIRSEQ_ROOT/examples/hubert/simple_kmeans/dump_km_label.py \
|
||||
$tgt_dir/mfcc $train_split $tgt_dir/mfcc/cls$dim 1 0 $tgt_dir/mfcc/cls${dim}_idx
|
||||
cp $tgt_dir/mfcc/cls${dim}_idx/${train_split}_0_1.km $tgt_dir/$train_split.km
|
||||
|
Loading…
Reference in New Issue
Block a user