Last modified 13 years ago Last modified on 12/12/07 06:47:49


Currently, we don't know of any freely licensed pronunciation dictionary for German. Thus, we will probably have to create our own.

eSpeak has pronunciation rules for German, but its phoneme inventory is much different from ours. Fortunately, we are not the only ones trying to convert it to a SAMPA-based phoneme set: Anybody interested in contactig Jan Pawellek?

There is now a tiny conversion script, based on the information in the cited forum post and the eSpeak sources.

Use it like this: espeak -v de -x -q 3>&1 1>&2 2>&3 | ./

Then type some words and see the conversion.

The 3>&1 1>&2 2>&3 voodoo is necessary as espeak outputs its phonemes on stderr instead on stdout.

The script is available here and can soon be downloaded from the SVN.

Important Note

The output of the above script is not perfect. Not at all. This is partly due to espeak, partly to the conversion script. In order to build our dictionary, we will have to hand-correct it.