This is the official Idlak readme. This is a fork of [the ASR toolkit Kaldi] (https://github.com/kaldi-asr/kaldi), with various tools and examples added to make it suitable for Text-to-Speech.
Idlak is a project to build an end-to-end parametric TTS system within Kaldi, to be distributed with the same Apache 2 licence. It contains a robust front-end, voice building tools, speech analysis utilities, and DNN tools suitable for parametric synthesis. It also contains an example of using Idlak as an end-to-end TTS system, in idlak-egs/tts_tangle_arctic/s2
Note that the kaldi structure has been maintained and the tool building procedure is identical.
I assume that the reader would like to (1) build the toolkit and (2) run the example system builds.
To build the toolkit: see ./INSTALL. These instructions are valid for UNIX
systems including various flavors of Linux; Darwin; and Cygwin (has not been
tested on more "exotic" varieties of UNIX). For Windows installation
instructions (excluding Cygwin), see windows/INSTALL.
The documentation should be build separately, cf. src/doc/README. Normally this documentation is generated by running "doxygen" from the src/ directory, and appears in src/html/
To run the example system builds, see egs/README.txt.
If you are reading this, you probably want to build the "Tangle" demo, which is located idlak-egs/tts_tangle_arctic/s2.
If you encounter problems (and you probably will), please do not hesitate to contact the developers (see below). In addition to specific questions, please let us know if there are specific aspects of the project that you feel could be improved, that you find confusing, etc., and which missing features you most wish it had.
Most of Idlak specific bug / features request should be put as "Issues" using the github bug tracking system. Usage questions should be directed to the kaldi-help mailing list, please see below.
For HOT news about Kaldi see the project site.
- Info about Idlak
- Info about language and audio resources
- Doxygen reference of the Idlak and Kaldi C++ code.
- Info about the project, description of techniques, tutorial for C++ coding.
- Doxygen reference of the Kaldi C++ code.
Kaldi forums and mailing lists:
We have two different lists
- User list kaldi-help
- Developer list kaldi-developers:
To sign up to any of those mailing lists, go to http://kaldi-asr.org/forums.html:
- Create a personal fork of the main Idlak repository in GitHub.
- Make your changes in a named branch different from
master, e.g. you create a branchmy-awesome-feature. - Generate a pull request through the Web interface of GitHub.
- As a general rule, please follow Google C++ Style Guide. There are a few exceptions in Kaldi & Idlak. You can use the Google's cpplint.py to verify that your code is free of basic mistakes.
- Kaldi is expected to work out of the box in RHEL >= 7 and Ubuntu >= 16.04 with OpenBLAS, ATLAS, or CUDA.
- CUDA drivers for ppc64le can be found at https://developer.nvidia.com/cuda-downloads.
- An IBM Redbook is available as a guide to install and configure CUDA.
- Kaldi supports cross compiling for Android using Android NDK, clang++ and OpenBLAS.
- See this blog post for details.