Use logprobs, fix beam candidate selection

Incorrect sort condition resulted in worst 5 beams being picked instead of
best 5.

Use log probabilities for joint probability calculation instead of
linear probabilities. Long beams would have probabilities converge
exponentially towards zero; now they converge linearly towards
-INFINITY.

Using both transcripts in Evaluation/setup.ps1, I see a small edit
distance regression (~5%) using beam search vs. greedy.

0 files changed, 0 insertions, 0 deletions