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
  • Makefile.unix
  • 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
  • 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 2.2.025Oct24212019181454230Sep2928272416157654Aug24Jul22151210976530Jun2827262513May2Apr131Mar211774225Feb242119171613119765432131Jan30292827252419181418Dec1410Nov30Oct2521201995427Sep152117Aug14134229Jul2018161514131110730Jun2926252421181510712May2Mar19Feb123Jan18171623Dec19826Nov2128Oct21Aug191715108231Jul720Jun181514131413118125May10926Apr21201323Mar914Feb10319Jan4Dec313Oct225Sep2438Jul4Jun31May26Apr141211109873128Mar2724222019181715141211125Feb19181615141312131Jan302924232120179129Dec281615131211109764130Nov29282726252423227331Oct302524232221added some prototypes to header fileupdated source file listfinished encoder implementationadded re-ordering to dred_rdovae_decode_qframe (frames now in correct order)added destroy functions for encoder/decoder statesfixed theta and r valuesMerge branch 'exp_rdovae6' of https://github.com/xiph/LPCNet into exp_rdovae6added api functions for retrieving pointers to statistical model parametersfixed type error for statistical modelmore fixesadded dred encoder to silk encoderbugfixesbugfix in dred_rdovae.caded api for DRED/RDOVAE to circumvent conflicts between Opus and LPCNet repoadded void to shut up missing prototype warningremoved compute_dense function (conflict with opus mlp)refactoringadded NFEC decoder C implementationadded statistical model to dump_nfec_modelbugfixes in nfec encodersome fixesfirst attempt of C implementation of fec encoder (not tested yet due to NEON/DOT_PROD not being separable)Fine-tuning the scriptsCompute FEC features based on loss patternUpdating fec_encoder.py for recent changesChange decoder architecture to be like the encoderWeighting loss by 1/sqrt(lambda)Larger range of quantizersremoved dump_data delay from total_delay in fec_encoder.pyCompletely move quantization out of encoder and decoderclarifications in help printoutfixed decoder bug (non-quantized input)alignment fix in fec_encoderported debug changes from fec_encoder_torch.pyUse the encoder state as decoder initial stateOops, forgot to run PVQ quantization for the statecorrected offset between decoder output on even/odd latent framesMerge branch 'exp_rdovae6' of https://github.com/xiph/LPCNet into exp_rdovae6added missing dead-zone to encode_rdovae.pyadded fec_encoder.py and corresponding fec_packets.[chpy]