Import 40.000 German words

You can import Ralf’s German dictionary (version 0.1.1) with more than 40.000 words into simon. Download the dictionary, then import it into simon:

dictionary

I hope that it works with simon. I didn’t use it for training. But it should work. It contains many known errors.

Standards of this dictionary: PLS, GPL, IPA, UTF-8.

If there are compatibility issues with simon, please report back.

It might be possible to convert this lexicon into a BOMP compatible format. I would need a way to get information about the terminals (= Wortarten). I don’t know at the moment how I could achieve this goal.

Tags: , ,

3 Responses to “Import 40.000 German words”

  1. producer says:

    I will have to sort out words with a french vowel like “Engagement”.

  2. [...] testing simon my first steps with the simon speech recognition software « Import 40.000 German words [...]

  3. [...] are the differences to version 0.1.1: – increased the size of the dictionary (from about 40.000 words to more than 100.000); – removed duplicate graphemes/phonemes; – improved phoneme quality, e.g. the [...]