-
I am using Tacotron2 trained on a custom dataset on V3 Config, along with a custom trained ParallelWaveGAN FROM @kan-bayashi implementation. Everything works well but i have two concerns.
Q1 - Is t…
-
I have an algorithm that updates in a loop but with differing behavior for even and odd steps, so very simplified, I have the following
```python
def my_func(i, *other_inputs):
if i % 2 == 0:
…
lumip updated
4 years ago
-
Hi, I noticed that the IoU number under "4.1 3D Reconstruction on ShapeNet" section in MarrNet paper is 0.57, what class is this IoU for? Or is it the average IoU over the chair, plane and car classes…
-
Does this got any blog or attempt on do tts on Chinese?
-
Thanks for publishing the code and basic training instructions!
## Environment
**Datasets:** (9,063 speakers)
- LibriTTS (train-other-500)
- VoxCeleb1
- VoxCeleb2
- OpenSLR (42-44, 61-66, 69…
-
**Describe the bug**
A very high CPU usage caused by activating only this ltex extension (caused by java-9-oracle)
**Steps to reproduce**
1. Open latex files
2. Activate ltex extension
3. Obs…
-
The common voice project is meant for voice recognition, but some donors are recording tenth of hours and it is possible to separate their recordings out of the dataset. If we could train mimic2 based…
-
So i am trying to train Tacotron 2 on some custom dataset, i have a single speaker dataset, that is roughly around 11 hours.
I have trained other implementations of tacotron 1 before, and on this …
-
@CorentinJ Hello, I am confused with the component of training dataset for synthesizer and vocoder. Is it trained on the whole librispeech (clean and other, totally 960) or only on librispeech train-o…
-
Hi,
Thanks a million for your work on this package! A real lifesaver now that the old API is officially gone.
I was wondering whether CreateHIT's question argument can deal with crowd-form eleme…