RN it's very unclear how we're actually supposed to get a model to use with ctcdecode
I compile KenLM separately and do kenlm/bin/lmplz etc, but it seems to me that ctcdecode could somehow wrap this, the actual implementation is beyond me but anyone have any ideas for what would be a good approach to this?
RN it's very unclear how we're actually supposed to get a model to use with ctcdecode I compile KenLM separately and do kenlm/bin/lmplz etc, but it seems to me that ctcdecode could somehow wrap this, the actual implementation is beyond me but anyone have any ideas for what would be a good approach to this?