Automatic_Speech_Recognition icon indicating copy to clipboard operation
Automatic_Speech_Recognition copied to clipboard
verified publisher icon zzw922cn

timit_preprocess.py

Open duxiansheng opened this issue 8 years ago • 5 comments

I can't read timit, the problem is ValueError: File format 'NIST'... not understood. can you help me?

duxiansheng avatar Apr 06 '17 03:04 duxiansheng

You should convert the format of your audio first~

zzw922cn avatar Apr 11 '17 11:04 zzw922cn

@duxiansheng I use sndfile converter to convert NIST to WAV. Please refer to this repo and their home page. The TIMIT files you downloaded maybe ended with .wav, but they actually are NIST files. So you need to rename them as .nist before using sndfile to do converting.

brianlan avatar Apr 19 '17 14:04 brianlan

@duxiansheng @brianlan nst2wav script has been updated just now, it's in the feature folder.

zzw922cn avatar Apr 20 '17 02:04 zzw922cn

I can covert it with Auducity,but there are a lot of work to do. And is there a way to covert all of .wav by code?

duxiansheng avatar May 05 '17 07:05 duxiansheng

@duxiansheng yes, you can see my new code in timit or libri or wsj, it can automatically process both wav and nist files.

zzw922cn avatar May 05 '17 07:05 zzw922cn