Recent changes to Home

Discussion for Home page

shashi — Tue, 11 Sep 2018 07:43:32 -0000

Sorry Dan..
I'll make my question clear to you.

Using kaldi is it possible to translate a stram of 6-8 hours audio into text?

Discussion for Home page

shashi — Mon, 10 Sep 2018 11:12:41 -0000

Hello,
Can Any one provide the limitations for kaldi usage such as, how it works on realtime data?
can we stream data for 6-8 hours?
speaking recoginization based on time window?

Discussion for Home page

Vaibhav — Thu, 05 Jul 2018 05:36:14 -0000

Thanks for helping out
Is there any other thing i can try to reduce WER % ?

Discussion for Home page

Vaibhav — Wed, 04 Jul 2018 08:03:31 -0000

I saw wrong file Sorry .
It was 40

How can i improve accuracy ?

Discussion for Home page

Vaibhav — Wed, 04 Jul 2018 06:54:01 -0000

testing speakers are different
phone set size = 170
Yes , testing words exist in the the 1400 words

Discussion for Home page

Vaibhav — Wed, 04 Jul 2018 06:43:27 -0000

28 speakers for training and 4 for testing
90 minutes training data .
vocab size is 1400 words training .
I had trained using mono , tri1 , tri2 , tri3 and sgmm models but all are giving wer in range 55-65

Discussion for Home page

Vaibhav — Wed, 04 Jul 2018 06:17:32 -0000

i am not using any standard database .
I am having my own dataset of Punjabi language which is tonal language . So i thought it would be good to add pitch features with mfcc but the results are not good with or without pitch features .
What can i do ?

Discussion for Home page

Vaibhav — Wed, 04 Jul 2018 05:46:24 -0000

I am facing one more issue sir

I had run mfcc + pitch script with multiple available options
--add-pov-feature , --add-normalized-pitch etc .
but i am getting a WER % of about 55-60 %
Please suggest what can i do ?

Thanks

Discussion for Home page

Vaibhav — Wed, 04 Jul 2018 05:42:54 -0000

Ok Thanks for your help sir

Discussion for Home page

Vaibhav — Tue, 03 Jul 2018 10:00:14 -0000

I wanted to know that where i can found the script to extract pitch features only .
I know there is script for mfcc + pitch and plp + pitch features .
But i am unable to find the script to extract only pitch features .

Thanks