whisper : make beam candidate sort more stable (whisper/1943)

whisper : make beam candidate sort more stable (whisper/1943)

All else being otherwise equal, this encourages the beam candidate
selection to re-use the same decoder, which slightly
reduces the cache size.

I wouldn't expect it to make much of a performance difference,
but it helps when debug printing the cache and beam.

Added as part of understanding #1941.