-
# Task Name
Japanese Pitch Accent Recognition
## Task Objective
Pitch accent is an important feature in the Japanese language that distinguishes between words through variations in pitch. Eac…
-
Hi,
I tried out the algorithm to test on a few streetview images and am getting shorter heights than expected.
Learning from the earlier issues on Github, I used the customized 'vps_models/config…
-
### The Feature
As per my current understanding, there is no way to perform pre-processing on a request made via a pass through endpoint. For instance, the `async_pre_call_hook` seems to only be tr…
-
### 🚀 The feature, motivation and pitch
Hello,
I would like to know if there is any example/tutorial available to build a GNN model (layers architecture) with Pytorch Geometric for a regression …
-
Hi,
I'm trying to train `FastSpeech2` on my own data but I'm getting.
```bash
Traceback (most recent call last):
File "../../code/FastSpeech2.git/model/modules.py", line 121, in forward
…
-
**Describe the bug**
as the title says, grenade prediction doesn't work properly if you enable anti aim
**To Reproduce**
Steps to reproduce the behavior:
1- go to anti aim, select freestand, ena…
-
Thanks for the good job.
When I read the code , A question disturb me from understand it wholy: Why the pitch_predictor can predict pitch under different resolutions?
I see no difference when …
-
Thank you always for sharing your thoughtful code.
As we can see in FastPitch code, you added the pitch embedding to encoder output before passing the energy predictor.
https://github.com/NVIDIA…
-
## 🚀 Feature
## Motivation
While reading the ap calculation section of your pose branch source code, I noticed that you seem to be using bounding boxes for the ap calculation, rather than ke…
-
### 🚀 The feature
inference api should send json contents.
### Motivation, pitch
`
return [json.dumps(response)]
`
I use above code on postprocess() method. and I call inference api `/…