mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-08-10 10:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
Your Name 2024-10-24 00:43:16 -07:00
parent a6a80896d5
commit ce72b34c30
2 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
egs/librilight/SSL/local/extract_kmeans.py
View File

@ -18,6 +18,7 @@
import argparse import argparse
import logging import logging
import math import math
import os
from pathlib import Path from pathlib import Path
from typing import Optional from typing import Optional
@ -36,6 +37,8 @@ from tqdm import tqdm
torch.set_num_threads(1) torch.set_num_threads(1)
torch.set_num_interop_threads(1) torch.set_num_interop_threads(1)
os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "max_split_size_mb:512"
class ApplyKmeans(object): class ApplyKmeans(object):
def __init__(self, km_path): def __init__(self, km_path):

2
egs/librilight/SSL/prepare.sh
View File

@ -64,7 +64,7 @@ fi
if [ $stage -le 3 ] && [ $stop_stage -ge 3 ]; then if [ $stage -le 3 ] && [ $stop_stage -ge 3 ]; then
log "Stage 3: Split medium and large subset into pieces" log "Stage 3: Split medium and large subset into pieces"
num_per_split=2500 num_per_split=10000
split_dir=data/kmeans/medium_split split_dir=data/kmeans/medium_split
if [ ! -f $split_dir/.split_completed ]; then if [ ! -f $split_dir/.split_completed ]; then
lhotse split-lazy ./data/kmeans/librilight_cuts_medium_raw.jsonl.gz $split_dir $num_per_split lhotse split-lazy ./data/kmeans/librilight_cuts_medium_raw.jsonl.gz $split_dir $num_per_split