Alok Prasad

ok i was able to solve it , diff is here https://github.com/alokprasad/binaries/blob/master/squeezewave.diff I will request a pull request for the same .

@varungujjar you can use this repo , have put all the changes there https://github.com/alokprasad/fastspeech_squeezewave

Yes, that's the problem with pytorch , models are very difficult to convert to onnx/caffe or torch script. even if we are able to c/c++ code do not produces right...

@jyao1 1.2k is too small rather I thought? https://github.com/DMTF/libspdm/discussions/603 also show minimum size as 22k yes its release build. unit_test/test_size/test_size_of_spdm_responder/CMakeLists.txt uses below flags. SET(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -nostdlib -Wl,-n,-q,--gc-sections -Wl,--entry,ModuleEntryPoint") I cannot...

in Main CMakelists.txt we are using -flto -DUSING_LTO whic will removes all the function not used hence size is small. if i remove them compilation fails , to proceed i...

@Clouxie Try to use lpcnet c++ as vocoder .its quite fast .There are discussion and project using tacotron2 for generating mels( 20 coefficient ) and then lpcnet as vocoder for...

There seems to some work done by Gregor with this commit https://github.com/GregorR/rnnoise-nu/commit/53f34de7d95af80c0c9101c791db47a05ec36196 in github.com/GregorR/rnnoise-nu

@enting0608 @nerv3890 Where you guys able to Train Rnnoise using 16khz and attain same quality as with 48khz ? What are the changes required.

> If you make any change to the way the features are computed (which is the case if you change the number of bands), then you need to retrain all...

There seems to some work done by Gregor with this commit https://github.com/GregorR/rnnoise-nu/commit/53f34de7d95af80c0c9101c791db47a05ec36196 in github.com/GregorR/rnnoise-nu