not work in large model

[liangxiwei]

lige.aac.zip
whisper lige.aac --model large
it not work.
the output is:
Detecting language using up to the first 30 seconds. Use --language to specify the language
Detected language: Chinese
[00:00.000 --> 00:29.980] 字幕由 Amara.org 社群提供
[00:30.000 --> 00:59.980] 字幕由 Amara.org 社群提供
[01:00.000 --> 01:29.980] 字幕由 Amara.org 社群提供
[01:30.000 --> 01:59.980] 字幕由 Amara.org 社群提供
[02:00.000 --> 02:29.980] 字幕由 Amara.org 社群提供
[02:30.000 --> 02:59.980] 字幕由 Amara.org 社群提供
[03:00.000 --> 03:14.180] 字幕由 Amara.org 社群提供