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 2.2.016Jan15121110985422Dec2120191817161514131211876542130Nov292827262524232221201817161514111098763231Oct3029282724232120191817161514121110876432130Sep29282726252423222120161513125111Aug9843131Juladded relegance inspection tool to dnntoolsImproving PLCexp_plc_fix1exp_plc_fix1PyTorch code for training the PLC modelbugfixadded repeat_upsamp option to feature netadded option of having residual connections in NoLACE feature transformsadded recording of git diff when repo is dirtyAdd pitch_demoicassp2024icassp2024fixing git repo information in dnn/torch/osceenabling debug printout for sparsification (disable before merge)base sparsifier now really addedadded base class for sparsification modulessplit sparsification density according to layerssparsification now compatible with weight_normswitched to absolute scale in softquant.pymore sparsification stuffadded sparsification option to NoLACEremoved verbose outputadded sparsification to LACE modeladded conv1d and linear sparsification modulespushed some common tools into new dnntools folderswitched to optimal-scale soft quantizationremoved debug printsfixed softquant modulefix when pitch hangover = 0Prevent overshoots from CELT PLC with predictionexp_celt_plc_co…exp_celt_plc_constraint1Add simulated loss to opus_demoAdd simulated loss to opus_demoexp_sim_loss2exp_sim_loss2Make loss simulator standaloneC code for packet loss simulatorlossgen: better training, README.mdlossgen: can now dump weightsPacket loss generation modelupdated readmeenabled WB encoding below 9kb/s againfixupdated Readmeupdated README with ICASSP 2024 introosce enabled by default, dec_complexity=10divide max payload tooexp_multiframe_…exp_multiframe_cleanup3
Loading