LPCNet
LPCNet copied to clipboard
xiph
Efficient neural speech synthesis
Hi, have you ever met this problem? in "training_tf2/lpcnet.py", line 246, in new_lpcnet_model, ValueError: A `Concatenate` layer requires inputs with matching shapes except for the concat axis. Got inputs shapes:...
In the "complexity" section of https://jmvalin.ca/demo/lpcnet/, what does a network size of 61/122/etc refer to? Which variable does it correspond to in the python script lpcnet.new_lpcnet_model()? Is it rnn_units1?
Our project needs a smaller size A , is there any way to reduce the size of A ? The need for sound quality only needs to be discernible.
I think the trick in this surrounding "for" code block is to suppress insignificant, possible doubling period. Is there any more in-depth motivation, explanation, or paper mentioning this? Thanks. https://github.com/xiph/LPCNet/blob/2159b4f85d9839d9627f1843a1cb5ea298c63159/src/lpcnet_enc.c#L597
i want to know tf2 version code'requirements,i have tried many versions(tensorflow, keras,cuda...),so how can i run it?
## Summary Broken `MDense.get_config` crash model loading in Python. Estimated cause is wrong attribute name. With hacking, it can be fixed. ## Phenomena I tried to resume training from saved...
Hi, I have changed the model config like the size of gru_a and gru_b after the model train finished, I replaced the nnet_data.h and nnet_data.c, when rebuild , the md5sum...
Good morning, I'm currently dealing with a slightly different problem: I'm testing different networks on music signals, sampled at 32kHz. Do you think I can test your network on music...
[Full-Band LPCNet: A Real-Time Neural Vocoder for 48 kHz Audio With a CPU](https://xploreqa.ieee.org/document/9455356/) GPU is expensive and power-hungry.
