char-rnn comparison

[gsever]

Hello,

Another question. I know char-rnn has started all this. Are there any comparisons out there which compares the accuracy/speed of char-rnn and chainer implementation. Getting Torch installed is a bit headache for me so I am still staying Python side as much as possible. If all input parameters are same, could these two packages sample exact same text after same training. Let me know of your thoughts. Thanks.