loodos/electra-base-turkish-64k-uncased-discriminator

Turkish ELECTRA-Base-discriminator (uncased/64k) trained on uncased Turkish dataset . This version has a vocab of size 64k, different from default 32k . Currently, Huggingface's tokenizers (which were written in Python) have a bug concerning letters "ı, i, I, İ" and non-ASCII Turkish specific letters . Until it is fixed, in case you want to train your model with uncased data, we provide a simple text normalization module (TextNormalization() in the code snippet above) in our repo . Many thanks to TFRC Team for providing us cloud TPUs on Tensorflow Research Cloud,