-
Still working with just the manual.py script. Much appreciate your assistance. I'm using h256_nvenc for hardware acceleration. I have my video max-width = 1280. This combination create the following f…
-
compiling gnuradio, gnu-companion is disabled component. I think maybe it is because of PYTHONPATH. But i dont know how to deal with it.
would you please give me some instructions about it? thank y…
-
Hi,
I wish to time-stretch arrays with lengths between 150 and 1000 samples to new arrays with lengths within the same range.
However, e.g. when using `librosa.effects.time_stretch` on an array …
jwb95 updated
5 years ago
-
![step-30000-align](https://user-images.githubusercontent.com/6031938/38714938-2c8d73e4-3f0b-11e8-988e-31534924f98c.png)
![step-30000-pred-mel-spectrogram](https://user-images.githubusercontent.com/6…
-
Phase vocoder reduces audio quality and takes processing time, so it is a bad idea to keep it running if no tempo change is actually needed.
Switching over from vocoder to copying the stream (or b…
-
Hi @ar1st0crat thank you for wonderful library.
when I run the program , I got a error.
[qb010005.zip](https://github.com/ar1st0crat/NWaves/files/2786223/qb010005.zip)
using (var stream = ne…
-
Hey I am glad to inform you that I have succeeded to merge Tacotron model with World vocoder and generated some evaluation results as follows. The results sound not bad but still not perfect. However …
-
Hi,
first of all: thank you for this library!
I trying to use Aubio in iOS project, mainly for spectrogram creation. I have no idea how to do it. Maybe someone has a sample code on Swift how to …
-
Is there a reason for using lws?
Do you use reconstructed phase somewhere to improve quality?
Thanks in advance, Duvte.
-
Hi, everyone.
Firstly, I'd like to thank you for your excellent Tacotron-2 code! @Rayhane-mamah
I'm a rookie in TTS, and I'm trying to run this Tacotron-2 model on my server. But I came up with a pr…