CTCDecoder

The RNN output matrix of the **Mini example** testcase contains 2 timesteps (t0 and t1) and 3 labels (a, b and  representing the CTCblank).
Best path decoding (see left figure) takes the most probable label per timestep which gives the path "" and therefore the recognized text "" with probability 0.6\*0.6=0.36.
Beam search, prefix search and token passing calculate the probability of labelings.
For the labeling "a" these algorithms sum over the paths "a", "a" and "aa" (see right figure) with probability 0.6\*0.4+0.4\*0.6+0.4*0.4=0.64.
The only path which gives "" still has probability 0.36, therefore "a" is the result returned by beam search, prefix search and token passing.