Skip to main content
This is a pre-production deployment of Warehouse. Changes made here affect the production instance of PyPI (
Help us improve Python packaging - Donate today!

Read and write HTK and HTS files from python.

Project Description

This python package allows reading and writing of files in some of the formats used by Hidden Markov Model Toolkit (HTK) and HMM-based Speech Synthesis System (HTS). The following HTK / HTS file formats are currently supported:

  • alignment files (also known as “label” files)
  • decision tree question set files
  • decision tree files
  • raw vector sequence files, used by HTS for storing speech parameter sequences

Alignments, trees, etc are represented in memory using simple python data structures. Files in the above formats may be read into, or written from, these python representations.


Please see the file License for details of the license and warranty for htk_io.


For most purposes the simplest way to install htk_io is to use pip. For example in Debian and Ubuntu:

sudo apt-get install python-numpy
sudo pip install htk_io

The first command installs numpy from the system repository, since installing numpy using pip is generally not recommended. The second command installs the latest released version of htk_io on PyPI, together with any currently uninstalled python packages required by htk_io.

htk_io can also be installed in a virtualenv:

sudo apt-get install python-numpy
virtualenv --system-site-packages env
env/bin/pip install htk_io

The latest development version of htk_io is available from a github repository (see below).

To check that htk_io is installed correctly you can run the test suite:

python -m unittest discover htk_io


Examples of usage of various functions and classes are included in their docstrings. A few examples of files in the formats this package can read and write are provided in the example directory.


The source code is hosted in the htk_io github repository. To obtain the latest source code using git:

git clone git://

Development is in fact done using darcs, with the darcs repository converted to a git repository using darcs-to-git.

To install any currently uninstalled python packages required by htk_io:

sudo apt-get install cython python-numpy
sudo pip install -r requirements.txt


Please use the issue tracker to submit bug reports.


The author of htk_io is Matt Shannon.

Release History

Release History

This version
History Node


History Node


History Node


History Node


History Node


Download Files

Download Files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

File Name & Checksum SHA256 Checksum Help Version File Type Upload Date
htk_io-0.5.tar.gz (16.2 kB) Copy SHA256 Checksum SHA256 Source Mar 17, 2015

Supported By

WebFaction WebFaction Technical Writing Elastic Elastic Search Pingdom Pingdom Monitoring Dyn Dyn DNS Sentry Sentry Error Logging CloudAMQP CloudAMQP RabbitMQ Heroku Heroku PaaS Kabu Creative Kabu Creative UX & Design Fastly Fastly CDN DigiCert DigiCert EV Certificate Rackspace Rackspace Cloud Servers DreamHost DreamHost Log Hosting