Skip to content
Snippets Groups Projects
Select Git revision
  • 1.0.1
  • 1.0.x
  • 1.1.1
  • 1.1.2
  • 1.1.x
  • 1.4.x
  • analysis_fix1
  • analysis_fix2
  • burg_optimization
  • cng_fix
  • cng_fix2
  • draft
  • draft_wip
  • dred_bitrate
  • dred_bitrate2
  • dred_bitrate3
  • exp-fwgan-plc
  • exp-fwgan1
  • exp-fwgan10
  • exp-fwgan2
  • v1.5.2
  • v1.5.1
  • v1.5
  • v1.4
  • v1.3.1
  • v1.3
  • v1.3-rc2
  • v1.3-rc
  • v1.3-beta
  • v1.2.1
  • v1.2
  • v1.2-rc1
  • v1.2-beta
  • v1.1.5
  • v1.1.4
  • v1.2-alpha2
  • v1.2-alpha
  • v1.1.3
  • v1.1.2
  • v1.1.1
40 results
You can move around the graph by using the arrow keys.
Created with Raphaël 2.2.029Dec281615131211109764130Nov29282726252423227331Oct3025242322211614131093226Sep2524141210631Aug242221171614331Jul292827262524232113121110926Jun25242114129May2824171615146327Mar262423222112222Feb21201816151312830Jan261918161031Dec19716Nov109730Oct292386528Sep19151129Aug2419171126Jul2518171615141312628Jun262019161413109642131May30262524231710128Apr1327Mar226Feb2018171514109430Jan252423201817129522Dec2019171625Nov24232219181716151110765432131Oct29282721520Sep1916151487632131Aug3027252117151413121198765130Jul292827Clean up resources in projection testrefactoringREADME updateadded concat.sh scriptupdated READMEadded MakefileProperly delaying the pitch gainControlling training offsetShould make dump_data able to handle partial overlapMore work on making freq.[ch] more genericRemoving most of the full-overlap assumptions from freq.[ch]Missing #includeAvoiding an infinite loopMoving the frame out of lpcnet.c and into test_lpcnet.cMore cleanupGet rid of the TRAINING macroMove the common functions from dump_data.c to freq.cRename denoise.c to dump_data.c, rnnoise.h to freq.h...Remove more useless codeCleanup: Remove useless code (more to come)Add -test or -train optionVectorization testing codeError messagesrefactored for different machines, sgemv_accum16 using NEON intrisicschecks that files opened OKControlling per-gate sparsityFix flooring of the pitch periodFix DCT normalizationreduce memory use of training codeAvoid rounding the prediction multiple timesFix compileProduce at least ~14 hours of augmented speechAdd variable gain and responseChopping silence from the training datamake dump_data output LPC as converted from featuresCompute LPC from featuresDo proper saturationSupport for plain AVX with no FMARemove the need for useless exc and pred files
Loading