show probability score in beam mode

[huangruizhe]

When we list top N (N>1) variants of decoding in the --return_beams mode, can we have a probability score for each variant? It seems there is no such an option.
Thanks!

[jubang0219]

I want it too.
But, I could not find that option.

So, I added the following variable in line 448 of g2p_seq2seq/g2p.py.

output_scores = np.split(result["scores"], self.decode_hp.beam_size,
axis=0)

And then, print the score of each candidate.

print("%s %s (%.4f)%s" % (decoded_inputs, decoded_outputs,
np.exp(output_scores[k]), self.decode_hp.delimiter))

I think the output scores are logprob, so I used the np.exp() function.
(It is not clear whether the logprob is correct. )

Thanks!