acutually, i think you shoud set the param merge_repeated to False, so the result will keep the repeated char. decoded, log_prob = tf.nn.ctc_beam_search_decoder(logits, seq_len, merge_repeated=False).
so your Ground truth text in readme.md 'semantically' will not be recognized as 'semanticaly'
https://github.com/Belval/CRNN/blob/063349508bd95e8dfb6b2e1135a7f8d8dd1fbc39/CRNN/crnn.py#L167
acutually, i think you shoud set the param merge_repeated to False, so the result will keep the repeated char.
decoded, log_prob = tf.nn.ctc_beam_search_decoder(logits, seq_len, merge_repeated=False)
.so your Ground truth text in readme.md 'semantically' will not be recognized as 'semanticaly'