tlg runtime decode question

[Yymax-max]

for (int i = 0; i < nbest; i++) { kaldi::LatticeWeight weight; std::vector alignment; fst::GetLinearSymbolSequence(nbestlats[i], &alignment, &outputs[i], &weight); ConvertToInputs(alignment, &inputs[i], &times[i]); RemoveContinuousTags(&outputs[i]); likelihood[i] = -weight.Value2(); }

in ctc_wfst_beamsearch.cc why likelihood[i] = -weight.Value2() is not likelihood_[i] = -(weight.Value1()+weight.Value2())?

[robin1001]

It should be likelihood_[i] = -(weight.Value1()+weight.Value2()) if we want the sum of acoustic score and lm score.

[Yymax-max]

It should be likelihood_[i] = -(weight.Value1()+weight.Value2()) if we want the sum of acoustic score and lm score.

thank you for your answer ,i approve your answer, but why ctc_wfst_beamsearch.cc is likelihood[i] = -weight.Value2(),-weight.Value2() is likely acoustic score , only add it ,what the mean of the tlg

[robin1001]

https://github.com/wenet-e2e/wenet/pull/1116

Please see the PR, we use both acoustic and graph cost now.