repodiac/german_transliterate 5
Python module to clean and transliterate (i.e. normalize) German text including abbreviations, numbers, timestamps etc. It can be used to clean messy text (e.g. map peculiar Unicode encodings to ASCII) or replace common abbreviations in text in combination with various text mining tasks.
repodiac/espeak-ng_german_loan_words 2
Brief tutorial with code where you can automatically create a dictionary with ~10k German loan words for import into espeak-ng as additional phonemic improvement or extension. This is, for instance, useful with Text-to-Speech (TTS) tasks in order to improve preprocessing.
repodiac/german_compound_splitter 0
Compound splitter for German language ("Komposita-Zerlegung") based on large dictionary combined with highly efficient multi-pattern string search
A neural network intent parser
uncategorized scripts and code snippets hopefully useful to others, as well :-)
:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
startedrepodiac/german_transliterate
started time in 13 days
startedrepodiac/german_transliterate
started time in 13 days
fork jbk0418/german_transliterate
Python module to clean and transliterate (i.e. normalize) German text including abbreviations, numbers, timestamps etc. It can be used to clean messy text (e.g. map peculiar Unicode encodings to ASCII) or replace common abbreviations in text in combination with various text mining tasks.
fork in 13 days
fork X-CCS/german_transliterate
Python module to clean and transliterate (i.e. normalize) German text including abbreviations, numbers, timestamps etc. It can be used to clean messy text (e.g. map peculiar Unicode encodings to ASCII) or replace common abbreviations in text in combination with various text mining tasks.
fork in a month
startedrepodiac/german_transliterate
started time in 3 months