If merge_repeated is True, merge repeated classes in the output beams.
This means that if consecutive entries in a beam are the same,
only the first of these is emitted. That is, when the sequence is
A B B * B * B (where '*' is the blank label), the return value is:
A B if merge_repeated = True.
A B B B if merge_repeated = False.
3-D floatTensor, size [max_time x batch_size x num_classes].
1-D int32 vector containing sequence lengths, having size
An int scalar >= 0 (beam search beam width).
An int scalar >= 0, <= beam_width (controls output size).