-
I'd like to train my own TTS model in Italian, using the portion of the MAILABS dataset (~18 hours). If I train the Tacotron 2 model with this dataset (16 kHz) can I fine tune from a pre-existing Engl…
-
Hi there,
I learn Go and I try migrate to modules.
My env is
```
➜ ~ % go env
GO111MODULE="auto"
GOARCH="amd64"
GOBIN="/Users/vic/Dev/go/bin"
GOCACHE="/Users/vic/Library/Caches/go-build"
G…
-
https://github.com/NVIDIA/waveglow/issues/54
In this issue, they were talking about lower some parameters to maximize inference speed. But I dont know how to do it properly, what can be reduced and w…
-
I tried to drop a spectrogram sanmple as npy and feed HifiGAN but it gave me a lot of noise. I am wondering how good your results are, do you have samples with vocoders like above?
-
Hello,
in default setting, the vocoders are trained on mel-spectra computed from the real speech signals. When they are fed by the Tacotron-generated spectra, the quality is a bit lower.
I would l…
t-dan updated
2 years ago
-
I trained a speech model and the vocoder using the new version (espnet==0.10.6 and parallel_wavegan==0.5.4) and the synthesized voices have low quality. But when I use the old espnet (espnet==0.9.6 an…
-
the vocoder inference is taking more time to generate features like more than a minute how can I reduce it to milliseconds?
-
Hi author,
by using the provided checkpoint file of Hifi-gan to inference from mel-spectrograms extracted from AutoVC make_spect.py, I got a very low voice (the speaking speed was correct, though). …
-
**Type:** JSONDecodeError
**Text:** Expecting value: line 1 column 1 (char 0)
**Full:** Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 1950, in f…
-
As in the model.py file like: "/project/03-asvspoof-mega/lfcc-lcnn-lstmsum-p2s/01/model.py ", I don't understand why use def normalize_target(self, y): in line #272, I thought the target data was the…