-
Branch: Master ([540d811dd5](https://github.com/mozilla/TTS/tree/540d811dd52b5598a7cd21cbbcf197b0bfbeab62))
Hi,
trying to train a multi-speaker model using the current master branch with phonem…
-
## 🐛 Not necessarily a Bug
Not exactly a bug, but I think it makes more sense if the triangular Mel filterbanks are area-normalized, as opposed to the current behavior where they are height-normali…
-
Placeholder for issue related to integration of fastspeech with squeezewave
https://github.com/tianrengao/SqueezeWave
seems to quite faster than waveflow.
-
the load function is not loading a mp3 file
The code :
import os
import librosa
path = 'D:/fma_small/000/000002.mp3'
path = os.fspath(path)
y, sr = librosa.load(path, `duration=10)`
…
-
Hey!
I've trained text2mel part for mel generation for couple hundred epochs.
Model seems to be learning, and it gives somehow good results on different language dataset while fed to SSRN (withou…
-
## ❓ Questions and Help
### Please note that this issue tracker is not a help form and this issue will be closed.
We have a set of [listed resources available on the website](https://pytorch.org…
-
This is not a real issue, it's simply an example of the output when run on the conda environment I have been using to develop gatherup. The purpose is simply to give a quick idea of what the formatt…
-
Hello,
a got bus error when I was using the Onsets and Frames model.
**Reproducing code example:**
onsets_frames_transcription_transcribe --model_dir=«train/» a.wav (in terminal)
**Error messa…
-
Hello, is there any specific requirement on how to load our data? I suppose the dimensions have to be (batchesx1xsamples) but is there any specific constraint on the normalization?
-
Hi, as Eren requested, this is an issue to follow progress of the training a larger PWGAN model for multiple speakers.