search

wenet-e2e / wespeaker

Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit
Apache License 2.0
707 stars 116 forks source link

Unable to load shard #338

Open mrjunjieli opened 3 months ago

mrjunjieli commented 3 months ago

When the wespeaker is applied on torch>=2.1, it will output this error: "

[ WARNING : 2024-07-20 17:11:39,248 ] - error to parse id07100/uUtjsdtDOkQ/00327.wav.wav [ WARNING : 2024-07-20 17:11:39,248 ] - error to parse id07259/87pXFH7gTZw/00009.wav.wav [ WARNING : 2024-07-20 17:11:39,248 ] - error to parse id04222/KHa0QWgSUnA/00154.wav.wav ......

" I try to modify dataset/processor.py stream = tarfile.open(fileobj=sample['stream'], mode="r|*") -> stream = tarfile.open(fileobj=sample['stream'], mode="r:*") AND it works. I didn't try if it works on torch<2.1.

wsstriving commented 3 months ago

It seems it's the problem of tar, which is built in python, can you check whether the python version is the same?