search

k2-fsa / kaldi-decoder

Decoders from Kaldi using OpenFst
Apache License 2.0
22 stars 3 forks source link

acoustic-sclae option in kaldi decoder #6

Open armusc opened 8 months ago

armusc commented 8 months ago

Hi

is there a specific reason why the acoustic-scale option from kaldi decode-faster has not been exported as well? using kaldi decoding with icefall models allows to use some desirable properties like fst memory mapping with const fst but I have not been able to get same performance (in terms of WER) than icefall 1 best decoding (I observe higher deletion, for example) in icefall playing with the hlg-scale option seems to make same difference (like 10% relative from 0.2 to 0.8, for example) and I was wondering if I could observe the same difference by playing with the acoustic-scale option with kaldi decoder, but it is absent (it looks to me they are supposed to both play on the relative weight of graph and model scores during best path computation, isn't it?) I actually commented here https://github.com/k2-fsa/icefall/pull/1287#issuecomment-1783935747 but exporting a lattice decoder seems way more complicated, if possible at all

FredSRichardson commented 7 months ago

I wanted to second this. It can also be really useful to add a "length penalty" (actually a bonus when you have high deletion rates). Some decoders add costs for "space" any maybe word insertions as well. I don't know if these can all be thrown into the FST without violating "ring" constraints.