Yangang Cao

hi, I can‘t find CMakeLists.txt in root directory, can you please offer it? I want to test it on MacOS.

> Can you tell me which dataset you use for training? Hi, I do some changes as follow: Firstly, I add some clean music data into speech since I want...

I use original 48k speech (concatenate into a pcm, 15GB )and noise(concatenate into a pcm, 7.8GB), set count as 10000000, get increasing loss and nan again. When I set count...

Hi , I found the problem, the reason of increasing loss is following: ``` # print statistics running_loss += loss.item() # for testing print('[%d, %5d] loss: %.3f' % (epoch +...

> Hi @YangangCao > yes I was dumb, I only check for iter=1, epoch=1 that's why I didn't notice this printed loss increasing error on iteration. > I fixed on...

ok, thx

Hi @cookcodes I find your code is like this in denoise.c: ``` RNN_COPY(&st->pitch_buf[PITCH_BUF_SIZE-FRAME_SIZE], &st->comb_buf[COMB_BUF_SIZE-FRAME_SIZE*4], FRAME_SIZE); // 376 in denoise.c ... frame_analysis(st, X, Ex, &st->comb_buf[COMB_BUF_SIZE-FRAME_SIZE*4]); // 381 in denoise.c ``` however,...

https://alphacephei.com/vosk/install you can check this page and build binary from source. I had built binary in M1 Mac

ok got it, thanks for your quick and accurate reply!

Hi, sorry to bother you, I find some phone which is hard to read, for example electromagnetic electromagnetic @_B l_I E_I k_I t_I r_I oU_I m_I {_I g_I n_I E_I...