Mylly (”The Mill”) is a versatile platform for processing and analyzing language data. It is based on the open-source Chipster technology developed at CSC – IT Center for Science. In Mylly, you can analyze your data conveniently in your own workspace where you can select the tools you need from a menu. You can, for example, use parsers for lemmatizing and analyzing text or an automatic speech recognizer for your audio files. All the corresponding tools can also be used directly from the command line in CSC’s computing environment, if required.
|New! Mylly has been updated! The new Mylly works in a regular web browser and you can log in the new Mylly with your regular HAKA user account. You no longer need to install the Java platform for using Mylly.
Note that at the moment you need an affiliation to a Finnish university or a CSC project to use Mylly.
Please note that all of the tools that are available in the old Mylly may not yet work on the new platform, and you may run into some errors. The collection of tools will be growing in the coming months. Nevertheless, the new Mylly platform is recommended for all users, since the old Mylly version will no longer be updated.
Small examples of using Mylly (PDF, examples prepared for Interspeech 2017; the examples apply to the old Mylly version)
The Chipster technology was originally developed for bioscientific use but the principles presented in the instruction videos also work in language research.