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 2.2.024Nov23227331Oct3025242322211614131093226Sep2524141210631Aug242221171614331Jul292827262524232113121110926Jun25242114129May2824171615146327Mar262423222112222Feb21201816151312830Jan261918161031Dec19716Nov109730Oct292386528Sep19151129Aug2419171126Jul2518171615141312628Jun262019161413109642131May30262524231710128Apr1327Mar226Feb2018171514109430Jan252423201817129522Dec2019171625Nov24232219181716151110765432131Oct29282721520Sep1916151487632131Aug3027252117151413121198765130Jul29282726252422Dump Conv1D (didn't check weight ordering at all)Dump embeddingUsing non-cudnn version of the GRU for the weightsMore meaningful namesWork in progress translation to CRefactoring: Isolating the matrix-vector product in gemm_accum()Output directly to 16-bit (raw) PCMmissing scriptAdding the scripts used to train the RNN classifierTrivial sprintf to snprintf conversion. Some linkers warn about unbounded sprintf calls.Make float2int() static with VSRemove useless OPUS_SET_EXPERT_FRAME_DURATION() on CELTFixes misleading initialization with not enough zerosupdate checksumsProject name is LPCNetCleanupmoving hyper-parameters to new_lpcnet_model() argumentsremove import that no longer existss/CELPNet/LPCNet/Rename the current files to use the LPCNet name since they're no longer WaveNetRemove no longer used files (old wavenet and LPCNet implementations)most promising model for nowclear pitch features in testing tooLPC generation from the cepstral coefficients...Add diagonal to sparsity maskArbitrary 16x1 sparsenessBump LT version numbersv1.3v1.3Proper detection of _mm_cvtss_si32 for MS compilerRenaming compute_allocation to clt_compute_allocation() to avoid symbol clashesbetter training paramsAdding commentsAdding a README.mdReduce sampling temperature for voiced framesAdding some instructionsCleaning up the synthesis code...second RNNadd licenseremove unused/dead code
Loading