Skip to main content

Vokarys: dictation that runs on your own machine

Most dictation today is a round trip to someone else's GPU. That is fine until your voice is the part the model was never trained on — an accent, a speech difference, a bad microphone in a noisy room — and you have no way to make it adapt.

That is the problem Vokarys goes after. It is a desktop app that turns speech into text with recognition running locally on your computer, with punctuation and capitalisation added as you talk. It learns from your own voice over time, and recordings stay on the machine unless you explicitly choose to contribute them. There is a voice chat mode wired to Gemini as well, and a browser version if you would rather not install anything.

If you have given up on dictation because the generic model never quite got you, it is worth a look.

Labels:

Popular posts from this blog

Viterbi Algorithm in C++ and using STL

To practice my C++ and STL skills, I implemented the Viterbi algorithm example from the Wikipedia page:  http://en.wikipedia.org/wiki/Viterbi_algorithm . The original algorithm was implemented in Python. I reimplemented the example in C++ and I used STL (mainly  vector  and  map  classes).  This code is in public-domain. So, use it as you want.  The complete solution for MS Visual C++ 2008 can be found at  http://filip.jurcicek.googlepages.com/ViterbiSTL.rar // ViterbiSTL.cpp : is an C++ and STL implementatiton of the Wikipedia example // Wikipedia: http://en.wikipedia.org/wiki/Viterbi_algorithm#A_concrete_example // It as accurate implementation as it was possible #include "stdafx.h" #include "string" #include "vector" #include "map" #include "iostream" using namespace std; //states = ('Rainy', 'Sunny') //  //observations = ('walk', 'shop', 'clean') //  //start_probability = {'Rainy': 0.6...
6 comments
Read more

how the make HCL and G graphs, and on the fly compositon of HCL and G for KALDI

Well, I had again to do something ;-) The task is to generate/create/update a decoding graph for KALDI on the fly. In my case, I aim at changing a G (grammar) in the context of a dialogue system. One can generate a new HCLG but this would take a lot of time as this involves FST determinization, epsilon-removal, minimization, etc. Therefore, I tried to use on-the-fly composition of statically prepared HCL and G. At first, I struggled with it but later I made it work. See  https://github.com/jpuigcerver/kaldi-decoders/issues/1 Here is a short summary: At the end, I managed to get LabelLookAheadMatcher to work. It is mostly based on the code and examples in opendcd, e.g. https://github.com/opendcd/opendcd/blob/master/script/makegraphotf.sh . First, Here is how I build and prepare the HCL and G. Please not that OpenFST must be compiled with  --enable-lookahead-fsts , see http://www.openfst.org/twiki/bin/view/FST/ReadMe . #--------------- fstdeterminize ${lang}/...
2 comments
Read more

kaldi editing nnet3 chain model - adding a softmax layer on top of the chain output

I had to do one more thing: to edit a trained  kaldi  nnet3 chain model and add a softmax layer on top of the chain model. The reason for this is to get "probability" like output directly from the chain model First, let's look at the nnet structure: nnet3-am-info final.mdl input-dim: 20 ivector-dim: -1 num-pdfs: 6105 prior-dimension: 0 # Nnet info follows. left-context: 15 right-context: 15 num-parameters: 15499085 modulus: 1 input-node name=input dim=20 component-node name=L0_fixaffine component=L0_fixaffine input=Append(Offset(input, -1), input, Offset(input, 1)) input-dim=60 output-dim=60 component-node name=Tdnn_0_affine component=Tdnn_0_affine input=L0_fixaffine input-dim=60 output-dim=625 component-node name=Tdnn_0_relu component=Tdnn_0_relu input=Tdnn_0_affine input-dim=625 output-dim=625 component-node name=Tdnn_0_renorm component=Tdnn_0_renorm input=Tdnn_0_relu input-dim=625 output-dim=625 component-node name=Tdnn_1_affine component=Tdnn_1_affi...
Post a Comment
Read more