Category Archives: openFST

Porting openFST to java: Part 4

Notice: Parts of this article may be outdated. There are many changes to its API and performance improvements recently in the java fst framework.  Please refer to recent articles in Java FST Framework category for the latest info. Foreword This article, the fourth in a series regarding porting openFST to java, describes the latest version… Read More »

Porting openFST to java: Part 3

Notice: Parts of this article may be outdated. There are many changes to its API and performance improvements recently in the java fst framework. Please refer to recent articles in Java FST Framework category for the latest info. (originally posted at http://cmusphinx.sourceforge.net/2012/07/porting-openfst-to-java-part-3/) Foreword This article, the third in a series regarding, porting openFST to java,… Read More »

Automating the creation of joint multigram language models as WFST: Part 2

(originally posted at http://cmusphinx.sourceforge.net/2012/06/automating-the-creation-of-joint-multigram-language-models-as-wfst-part-2/) Foreword This a article presents an updated version of the model training application originally discussed in [1], considering the compatibility issues with phonetisaurus decoder as presented in [2]. The updated code introduces routines to regenerate a new binary fst model compatible with phonetisaurus’ decoder as suggested in [2] which will be… Read More »

Compatibility issues using binary fst models generated by OpenGrm NGram Library with phonetisaurus decoder

(originally posted at http://cmusphinx.sourceforge.net/2012/06/compatibility-issues-using-binary-fst-models-generated-by-opengrm-ngram-library-with-phonetisaurus-decoder/) Foreword Previous articles have shown how to use OpenGrm NGram Library for the encoding of joint multigram language models as WFST [1] and provided the code that simplifies and automates the fst model training [2]. As described in [1] the generated binary fst models with the procedures described in those articles… Read More »

Automating the creation of joint multigram language models as WFST

Notice: This article is outdated. The application described here is now part of the SphinxTrain application. Please refer to recent articles in CMUSphinx category for the latest info. (originally posted at http://cmusphinx.sourceforge.net/2012/06/automating-the-creation-of-joint-multigram-language-models-as-wfst/) Foreword Previous articles have introduced the C++ code to align a pronounciation dictionary [1] and how this aligned dictionary can be used in… Read More »

Using OpenGrm NGram Library for the encoding of joint multigram language models as WFST

(originally posted at http://cmusphinx.sourceforge.net/2012/06/using-opengrm-ngram-library-for-the-encoding-of-joint-multigram-language-models-as-wfst/) Foreword This article will review the OpenGrm NGram Library [1] and its usage for language modeling in ASR. OpenGrm makes use of functionality in the openFST library [2] to create, access and manipulate n-gram language models and it can be used as the language model training toolkit for integrating phonetisaurus’ model… Read More »

Porting openFST to java: Part 2

Notice: Parts of this article may be outdated. There are many changes to its API and performance improvements recently in the java fst framework. Please refer to recent articles in Java FST Framework category for the latest info. (originally posted at http://cmusphinx.sourceforge.net/2012/05/porting-openfst-to-java-part-2/) Foreword This article, the second in a series regarding, porting openFST to java,… Read More »

Porting openFST to java: Part 1

Notice: Parts of this article may be outdated. There are many changes to its API and performance improvements recently in the java fst framework. Please refer to recent articles in Java FST Framework category for the latest info. Foreword This article is the first part of a series of articles on porting openFST[1] in java.… Read More »