best-rq.png setup.py BEST-RQ - Pytorch Implementation ofBEST-RQ- a model for self-supervised learning of speech signals using a random projection quantizer, in Pytorch. This model can be used to generate semantic tokens for e.g.Spear-TTSorSoundStorm. ...
What does this PR do? fixes issue with normalizing on the wrong dimension in theRandomProjectionQuantizer fixes inconsistency with normalizer in pre-training and fine-tuning scripts makescompute_forwardfunction more efficient by only computing pseudo-targets on masked area...
AddRemove Datasets Edit Add Datasetsintroduced or used in this paper Results from the Paper Edit Submitresults from this paperto get state-of-the-art GitHub badges and help the community compare results to other papers. Methods Edit AddRemove...
Fixed the GitHub action created by the Qt Creator plugin wizard CMake: Fixed that user-defined `UTILITY` targets were missing from Locator Fixed a potential crash with CMake Presets Fixed an issue after updating MSVC Fixed that `CMakeLists.txt` could not be found when adding files when the...