wl3b10s
wl3b10s
i encode and decode a wav or pcm file with 16khz sample rate. the result pcm of opus_demo binary by opus source code contains all frequency information between 0-8khz. the...
when using training stage. i got "d_srgan.npz" not found. there is g_srgan download link in readme, but how to get d_srgan.npz?? thanks.
when the project is build with VS2015. error show: C1083 Cannot open include file: 'ogg/ogg.h': No such file or directory C1083 Cannot open include file: 'opus.h': No such file or...
i encode and decode a wav or pcm file with 16khz sample rate. the result pcm of opus_demo binary by opus source code contains all frequency information between 0-8khz. the...
with default setting, simply run train on VCTK without extra global condition by : python train.py then python generate.py --wav_out_path=testresult3900.wav --samples 320000 logdir/train/2020-10-22T13-35-57/model.ckpt-3900 seems doesn't generate voice wav but pure...
will you share your trained model? thanks
## ❓ Questions it seems the definition of 'loss_l' in figure 1 that connected vq and transofomer in the quantizer block is not described in the paper. it there some...
when i try to retrain DAC model, i found that commit_loss and codebook_loss always be equal for each iteration. is it correct? code location: quantize.py, class VectorQuantize commitment_loss = F.mse_loss(z_e,...
can descript-audio-codec works below 32kbps outperforms opus at 32kbps? the results in papers showed descript-audio-codec@8kbps has similar performance for opus@24kbps.
epoch: 65, time: 6.90/107.22, train_loss: 0.0074, val_loss: 0.0089, ER/F/LE/LR/SELD: 0.78/0.09/125.04/0.21/0.79, best_val_epoch: 62 (0.73/0.11/122.98/0.18/0.78) could not broadcast input array from shape (6,5,13) into shape (6,4,13) is there bugs to run with...