make-segments can't find segments
you'd want to break it up into smaller pieces, like 15 segments as the decoder doesn't handle too-long segments, but thaat's trivial. On Tue, Sep 11, 2018 at 3:43 AM shashi shashi1020@users.sourceforge.net wrote: 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? Sent from sourceforge.net because you indicated interest in https://sourceforge.net/p/kaldi/wiki/Home/ To unsubscribe from further messages, please visit https:/...
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?
see kaldi-asr.org/forums.html for how to ask questions, but your questions are very unclear. On Mon, Sep 10, 2018 at 7:12 AM shashi shashi1020@users.sourceforge.net wrote: 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? Sent from sourceforge.net because you indicated interest in https://sourceforge.net/p/kaldi/wiki/Home/ To unsubscribe from further messages, please visit...
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?
Thanks for helping out Is there any other thing i can try to reduce WER % ?
Sure, I will do that. On Thu, 5 Jul 2018, 12:14 am Daniel Povey, danielpovey@users.sourceforge.net wrote: Cool. I know that in China they have various dedicated lists. If you were to start one for Kaldi researchers in India it might be helpful. If you do, try to set it up so the archives are searchable (like kaldi-help) so that people can find it from google. Dan On Wed, Jul 4, 2018 at 2:34 PM, rohit kodali rohitgowtham@users.sourceforge.net wrote: Hi dan, I actively follow kaldi forums. I don't...
Cool. I know that in China they have various dedicated lists. If you were to start one for Kaldi researchers in India it might be helpful. If you do, try to set it up so the archives are searchable (like kaldi-help) so that people can find it from google. Dan On Wed, Jul 4, 2018 at 2:34 PM, rohit kodali rohitgowtham@users.sourceforge.net wrote: Hi dan, I actively follow kaldi forums. I don't think we have anything specially for indian or any other tonal languages, but if we have something for it...
Hi dan, I actively follow kaldi forums. I don't think we have anything specially for indian or any other tonal languages, but if we have something for it i would like to help the guys who are researching into them. I have been doing on these from kaldi beginning (proud to say first comment on kaldi is mine when released), tried almost all experiments on tonal languages on huge datasets collected by ourselves. On Wed, 4 Jul 2018, 11:50 pm Daniel Povey, danielpovey@users.sourceforge.net wrote: Rohit:...
Rohit: thanks for responding. For your guys' info, kaldi-help is the primary location for these discussions, see kaldi-asr.org/forums.html. There may be forums for Indian users of Kaldi too, which I am not aware of, and these, if they exist, would very very suitable for new users like Vaibhav. On Wed, Jul 4, 2018 at 4:34 AM, rohit kodali rohitgowtham@users.sourceforge.net wrote: Add More data from more speakers and get good phone tic coverage On Wed, 4 Jul 2018, 1:33 pm Vaibhav, ervaibhavkumar@users.sourceforge.net...
Add More data from more speakers and get good phone tic coverage On Wed, 4 Jul 2018, 1:33 pm Vaibhav, ervaibhavkumar@users.sourceforge.net wrote: I saw wrong file Sorry . It was 40 How can i improve accuracy ? Sent from sourceforge.net because you indicated interest in https://sourceforge.net/p/kaldi/wiki/Home/ To unsubscribe from further messages, please visit https://sourceforge.net/auth/subscriptions/
I saw wrong file Sorry . It was 40 How can i improve accuracy ?
170 phonemes for punjabi language i can see a max of 45 phonemes including silence for this ( if you use position dependent it will be 140 max), how you got 170 phone set. if you really have 170 phonemes then the phonetic coverage is too low for any phoneme in the training set. On Wed, Jul 4, 2018 at 12:24 PM Vaibhav ervaibhavkumar@users.sourceforge.net wrote: testing speakers are different phone set size = 170 Yes , testing words exist in the the 1400 words Sent from sourceforge.net because you...
testing speakers are different phone set size = 170 Yes , testing words exist in the the 1400 words What can be done ? Also i had tried training and testing on same speakers but again the WER was in range 60-75 %
testing speakers are different phone set size = 170 Yes , testing words exist in the the 1400 words
is the testing speakers are available in training or different What is your phone set size are the testing words exist in the the 1400 words and i don't think we get better accuracy with just 90 minutes of indian languages data On Wed, Jul 4, 2018 at 12:13 PM Vaibhav ervaibhavkumar@users.sourceforge.net wrote: 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...
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
Hi vaibhav, What is your dataset size and how many speakers, what is your training and testing vocabulary. Which model you have used for testing. To answer about wer we need to know these atleast. And how many phones in your lexicon for punjabi On Wed, 4 Jul 2018, 11:47 am Vaibhav, ervaibhavkumar@users.sourceforge.net wrote: 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...
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 ?
Hi, If you are using a standard speech database, can you mention it. Its easy to compare. On Wed, 4 Jul 2018 at 01:46, Vaibhav ervaibhavkumar@users.sourceforge.net wrote: 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 Sent from sourceforge.net because you indicated interest in < https://sourceforge.net/p/kaldi/wiki/Home/> To...
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
Ok Thanks for your help sir
kaldi doesn't live on sourceforge anymore. There isn't a script in steps/, but you can easily figure out how to write one if you understand Kaldi I/O mechanisms, with reference to the existing scripts. On Tue, Jul 3, 2018 at 6:00 AM, Vaibhav ervaibhavkumar@users.sourceforge.net wrote: Hi 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...
Hi 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
If the web interface does not work (for whatever reason), you can also subscribe...
If the web interface does not work (for whatever reason), you can also subscribe...
If the web interface does not work (for whatever reason), you can also subscribe...
I also would like to share some lines of the log files for mono_train.sh. 1. exp/mono/log/align.0.1.log...
Hi team Kaldi, I am trying to build an English ASR using my own data.It has 185 wav...
online decoding sample shows error after updating newer revesion
bug in shuffle_list.pl
Discussions and mailing lists are going offline!
All, we are phasing out using the sf.net mailing lists and moving to googlegroups.com....
All, we are phasing out using the sf.net mailing lists and moving to googlegroups.com....
All, we are phasing out using the sf.net mailing lists and moving to googlegroups.com....
ERROR! The markdown supplied could not be parsed correctly. Did you forget to surround...
Dear Dan Thank you very much. I solved this problem. The reason is as you said :...
ERROR! The markdown supplied could not be parsed correctly. Did you forget to surround...
ERROR! The markdown supplied could not be parsed correctly. Did you forget to surround...
BTW, in case anyone is getting these forum emails, please know that this forum, like...
Glad it's working. Seems the forum has almost an 1hr delay. y.
It looks to me like the issue was that for some reason the riff_chunk_size specified...
I am currently doing sox --ignore-length and this increases the number of samples...
I am currently doing sox --ignore-length and this increases the number of samples...
ERROR! The markdown supplied could not be parsed correctly. Did you forget to surround...
ERROR! The markdown supplied could not be parsed correctly. Did you forget to surround...
ERROR! The markdown supplied could not be parsed correctly. Did you forget to surround...
ERROR! The markdown supplied could not be parsed correctly. Did you forget to surround...
ERROR! The markdown supplied could not be parsed correctly. Did you forget to surround...
an example of a wav file is attached.
I will send a wav file to you.
I will send a wav file to you.
That does not help. The number of data bytes still remain odd because the the number...
ERROR! The markdown supplied could not be parsed correctly. Did you forget to surround...
That does not help. The number of data bytes still remain odd because the the number...
ERROR! The markdown supplied could not be parsed correctly. Did you forget to surround...
I have obtained single channel files from stereo data with 8 bit sample encoding....
I have obtained single channel files from stereo data with 8 bit sample encoding....
ERROR! The markdown supplied could not be parsed correctly. Did you forget to surround...
Is there a way to install KALDI currently with the sf service under maintenance?...
Dan, thanks for your help.
Everything looks right in what you described. Possibly there was a mismatch in a...
Dear all I wrote the below grammar : <s> = <hi> <names>; <hi> = hi | hello; <names>...
Dear all I wrote the below grammar : <s = <hi> <names>; <hi> = hi | hello; <names>...
Dear all I wrote the below grammar : = <hi> <names>; <hi> = hi | hello; <names> =...
Dear all I wrote the below grammar : = <hi> <names>; <hi> = hi | hello; <names> =...
Possibly it is trying to do a split where validation-set speakers are distinct from...
Hello, I am going to run DNN in Kaldi. In the script, egs/rm/s5/local/nnet/run_cnn.sh...
Hello, I am going to run DNN in Kaldi. In the script, egs/rm/s5/local/nnet/run_cnn.sh...
A tiny utility
trunk: minor fix to last trunk commit RE cu-dev...
sandbox/nnet3: merge changes from trunk: also a...
trunk: modifying cu-device.cc to work around wh...
No problem thanks for fixing it
Hi, it sholud be working well now! Thanks for finding the bug! K.
trunk,nnet1,mmi : bugfix in inital data filteri...
Yes it is. We should both thank to 'Lukas Burget', he is the original author of the...
Yes, it is actually a very cool feature from awk that lets you control the parsing...
Ok, I'll fix that. Thanks for finding the bug! K. Dne 15. 7. 2015 v 13:32 Daniel...
Hi, the problem is that you pre-trained only 5 layers, while the DNN training script...
Karel, could you please fix this? I think a comment explaining what the "r=1" thing...
Hi Dan, you were absolutely right the problem was that the $dir/lat.scp produced...
ERROR! The markdown supplied could not be parsed correctly. Did you forget to surround...
What you are encountering is instability; it is a common problem in neural network...
Hi Yenda, Yes gunzip is on the path. I even unzip the files into a common one and...
Hi All, I want to setup using global learning rate instead of learning rate matrix,...
I haven't looked into tuning that particular setup. You could just use all-defaults....
Hi All, Can anyone share your experience about below online natural gradient configuration...
I don't think his issue is coming from his archive that starts with "gunzip". I think...
Those objective function improvements are too large- they should be around 10. It...
ERROR! The markdown supplied could not be parsed correctly. Did you forget to surround...
Hi everyone, I have been trying to use the train_mmi.sh to train a model using boosted...
I would start with wsj since it is a large vocabulary task. It is very well commented...
Hi, I am having a look at Kaldi, I'd like to train large-vocabulary speaker-independent...
Hi, I am having a look at Kaldi, I'd like to train large-vocabulary speaker-independent...
Thanks a lot, I have found the reason. I have ever changed the configuration "nn_depth=5",...
Hi Dan, I found the mistake, the problem is I used the wrong ivector extractor. Thank...
The first error is "ERROR (nnet-concat:Input():kaldi-io.cc:672) Error opening input...
Hello everyone, I am a fisher. When I use kaldi to handle my own corpus(Chinese audios),...
Ok, thx ;) My previous "troubles" during the next steps of DNN training were related...