mirrors/icefall
1
0
Fork 0
mirror of https://github.com/k2-fsa/icefall.git synced 2025-12-11 06:55:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

from local

Browse Source
This commit is contained in:
dohe0342 2023-03-13 14:29:41 +09:00
parent 122ab29aab
commit 0f5eea55da
2 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
egs/librispeech/ASR/local/.prepare_vox.py.swp
View File

Binary file not shown.

8
egs/librispeech/ASR/local/prepare_vox.py
View File

@ -59,9 +59,10 @@ def prepare_vox(
# ) # )
manifests = {} manifests = {}
subset = spk_id.split('_')[0]
spk_idx = spk_id.split('_')[1]
#dataset_parts = ["train", "dev", "test"] #dataset_parts = ["train", "dev", "test"]
dataset_parts = [spk_id] dataset_parts = [spk_idx]
if output_dir is not None: if output_dir is not None:
output_dir = Path(output_dir) output_dir = Path(output_dir)
output_dir.mkdir(parents=True, exist_ok=True) output_dir.mkdir(parents=True, exist_ok=True)
@ -81,7 +82,8 @@ def prepare_vox(
#part_file_names = list(map(lambda x: x.strip('.wav'), os.listdir(part_path))) #part_file_names = list(map(lambda x: x.strip('.wav'), os.listdir(part_path)))
part_file_names = sorted(glob.glob(str(part_path)+'/*.wav')) part_file_names = sorted(glob.glob(str(part_path)+'/*.wav'))
part_file_names = [name.split('/')[-1].replace('.wav', '') for name in part_file_names] part_file_names = [name.split('/')[-1].replace('.wav', '') for name in part_file_names]
txt_path = os.path.join(corpus_dir, f"../{spk_id}/texts") txt_path = os.path.join(corpus_dir, f"../{spk_idx}_texts")
print(txt_path)
futures = [] futures = []
for trans_path in tqdm( for trans_path in tqdm(