The RWTH extensible training framework for universal recurrent neural networks.

Date Version URL
06/01/2016 v0.1 Download
most recent trunk GitHub repository

Please read the license information carefully before downloading the software.


The RWTH Extensible Training framework for Universal Recurrent Neural Networks (RETURNN) License

This license is derived from the Q Public License v1.0 and the Qt Non-Commercial License v1.0 which are both Copyright by Trolltech AS, Norway. The aim of this license is to lay down the conditions enabling you to use, modify and circulate the SOFTWARE, use of third-party application programs based on the Software and publication of results obtained through the use of modified and unmodified versions of the SOFTWARE. However, RWTH remain the authors of the SOFTWARE and so retain property rights and the use of all ancillary rights. The SOFTWARE is defined as all successive versions of RETURNN software and their documentation that have been developed by RWTH. When you access and use the SOFTWARE, you are presumed to be aware of and to have accepted all the rights and obligations of the present license:

  1. You are granted the non-exclusive rights set forth in this license provided you agree to and comply with any and all conditions in this license. Whole or partial distribution of the Software, or software items that link with the Software, in any form signifies acceptance of this license for non-commercial use only.

  2. You may copy and distribute the Software in unmodified form provided that the entire package, including - but not restricted to - copyright, trademark notices and disclaimers, as released by the initial developer of the Software, is distributed.

  3. You may make modifications to the Software and distribute your modifications, in a form that is separate from the Software, such as patches. The following restrictions apply to modifications:

  4. You may distribute machine-executable forms of the Software or machine-executable forms of modified versions of the Software, provided that you meet these restrictions:

  5. You may use the original or modified versions of the Software to compile, link and run application programs legally developed by you or by others.

  6. You may develop application programs, reusable components and other software items, in a non-commercial setting, that link with the original or modified versions of the Software. These items, when distributed, are subject to the following requirements:

  7. Users must cite the authors of the Software upon publication of results obtained through the use of original or modified versions of the Software by referring to the following publication: P. Doetsch, A. Zeyer, P. Voigtlaender, I. Kulikov, R. Schluter, and H. Ney, "RETURNN: The RWTH extensible training framework for universal recurrent neural networks", submitted to Interspeech 2016.

  8. In no event shall the initial developers or copyright holders be liable for any damages whatsoever, including - but not restricted to - lost revenue or profits or other direct, indirect, special, incidental or consequential damages, even if they have been advised of the possibility of such damages, except to the extent invariable law, if any, provides otherwise. The Software and this license document are provided "AS IS" with NO EXPLICIT OR IMPLICIT WARRANTY OF ANY KIND, INCLUDING WARRANTY OF DESIGN, ADAPTION, MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.

  9. You assume all risks concerning the quality or the effects of the SOFTWARE and its use. If the SOFTWARE is defective, you will bear the costs of all required services, corrections or repairs.

  10. This license has the binding value of a contract.

  11. The present license and its effects are subject to German law and the competent German Courts.

You may download, install and use the Software only when you agree with the terms of this license agreement.


RETURNN is based on Theano. The license information about Theano can be found here:


$ pip install theano h5py


Consult the demos folder to see example usages.