I've recently experienced this error AttributeError: 'BPECodesAdapter' object has no attribute 'read' which comes from the package _subwordnmt used during the tokenization. Apparently, this package had some modifications. It's better to fix the specific version during installation of laserembeddings to avoid the problem, i.e. pip install subword-nmt==0.3.7
I've recently experienced this error
AttributeError: 'BPECodesAdapter' object has no attribute 'read'
which comes from the package _subwordnmt used during the tokenization. Apparently, this package had some modifications. It's better to fix the specific version during installation of laserembeddings to avoid the problem, i.e.pip install subword-nmt==0.3.7