speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix data dir filter bug

Browse Source
This commit is contained in:
仁迷 2023-02-27 14:47:32 +08:00
parent 2432fc9c39
commit b6a1c6c1e6
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
funasr/utils/wav_utils.py
View File

@ -305,11 +305,11 @@ def filter_wav_text(data_dir, dataset):
wav_dict[sample_name] = wav_path
text_dict = {}
for line in text_lines:
parts = line.strip().split(" ", 1)
parts = line.strip().split()
if len(parts) < 2:
continue
sample_name, txt = parts
text_dict[sample_name] = txt
sample_name = parts[0]
text_dict[sample_name] = " ".join(parts[1:])
filter_count = 0
with open(wav_file, "w") as f_wav, open(text_file, "w") as f_text:
for sample_name, wav_path in wav_dict.items():
@ -318,4 +318,4 @@ def filter_wav_text(data_dir, dataset):
f_text.write(sample_name + " " + text_dict[sample_name] + "\n")
else:
filter_count += 1
print("{}/{} samples in {} are filtered because of the mismatch between wav.scp and text".format(len(wav_lines), filter_count, dataset))
print("{}/{} samples in {} are filtered because of the mismatch between wav.scp and text".format(len(wav_lines), filter_count, dataset))