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 2.2.09Aug843131Jul302827262423222012111097330Jun2827232221201918161514131265131May30292827262524232220191817161514131211109827Apr262019171422Mar17107621Feb1531Jan272625201713121121Dec2019161398762130Nov28242310987431Oct262524212019181454230Sep2928272416157654Aug24Jul22151210976530Jun2827262513May2Apr131Mar211774225FebMaking it easier to remove DRED experimental IDimproved auto-scaling in wexchangeUse FWGAN instead of LPCNet in PLCexp-fwgan-plcexp-fwgan-plcAdd fwgan_load_model()int version for convenienceAdding some commentsContinuation now workingMore scaling/filtering to run_fwgan_subframe()More FWGAN refactoringFWGAN refactoringApplying continuation after first subframeAvoid sin()/cos() calls for pitch referenceDon't compute linear activation in-placeAdd FWGAN to lpcnet_demoexp-fwgan10exp-fwgan10C implementation of FWGANSkeleton for FWGAN codeHandle float matrices with multiple of 8 rowsBring back support for non-multiples of 8exp-fwgan8exp-fwgan8Add FWGAN to lpcnet_demoC implementation of FWGANSkeleton for FWGAN codeHandle float matrices with multiple of 8 rowsAdd Gated Linear Unit (GLU)updated dump_model_weights.pyadded FWGAN weight dumping codeupdadet wexchange version numberadded .copy() to weights in wexchangeadded auto-scaling to wexchangeAdd pre-emphasis filter before LPC filterexp-fwgan2exp-fwgan2Delay gain by one subframeFixes GLU for framewise convolutionsdouble-precision phase to make debugging easierConcat embedding and conditioning in right orderAdd correlation offset to match Python codeFix corr featureFix conditioning sizeUse correct LPC weighting gamma valueUse correct output scalingHandle float matrices with multiple of 8 rowsactual zeros
Loading