UnicodeEncodeError When Training With Different Encoding

hunkim / word-rnn-tensorflow

Multi-layer Recurrent Neural Networks (LSTM, RNN) for word-level language models in Python using TensorFlow.

MIT License

1.3k stars 494 forks source link

Open murthyn opened 6 years ago

murthyn commented 6 years ago

I first trained the seq to seq model using a UTF-8 encoding (instead of the default ASCII). When sampling from this model, I get the following error:

UnicodeEncodeError: 'ascii' codec can't encode character '\u2018' in position 58: ordinal not in range(128)

How can I fix this?