devmount/GermanWordEmbeddings
Toolkit to obtain and preprocess German text corpora, train models and evaluate them with generated testsets. Built with Gensim and Tensorflow.
Jupyter NotebookMIT
Issues
- 2
Use already trained model
#36 opened by Enoo58 - 1
saving full model?
#33 opened by bernardo-cruz - 2
- 5
Provide citation info
#19 opened by LinqLover - 5
plain text to segments
#16 opened by Tortoise17 - 4
UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 0: ordinal not in range(128)
#13 opened by haemi - 6
Tests should be lowercased
#8 opened by prabhakar267 - 3
Error in preprocessing.py
#11 opened by POMCP - 5
- 2
Invalid Load Key Error
#9 opened by POMCP - 2
model evaluation & two error messages
#3 opened by matinho13 - 1
Function deprecated
#1 opened by tlubitz - 7
german.model done with skip-gram or CBOW?
#4 opened by matinho13 - 2
Error trying to load "german.model"
#5 opened by davidsbatista - 4