OpenGrm NGram Library

OpenGrm NGram Version 1.0.3 is now available for download.

The OpenGrm NGram library is used for making and modifying n-gram language models encoded as weighted finite-state transducers (FSTs). It makes use of functionality in the OpenFst library to create, access and manipulate n-gram models. Operations for counting, smoothing, pruning, applying, and evaluating models are among those provided. It was developed by contributors from OHSU and Google Research. It is an open source project distributed under the Apache license.

• Quick Tour
  • Corpus I/O
  • Model Format
  • N-gram Counting
  • N-gram Model Parameter Estimation
  • N-gram Model Merging and Pruning
  • Model Reading, Printing and Info
  • N-gram Model Sampling, Application and Evaluation
  • Using the C++ Library
  • Available Operations
• Download
• Development
• Forum
• Contributed and related projects