Comments (7)
@Psarpei those hyperparameters got set through the discussion here
maybe they can weigh in?
from bs-roformer.
If you use a compatible length, the length of the output will be the same as the length of the input. You are not losing anything this way. If you need to apply it to longer audio snippets, check out the part of the paper that describes overlap&average (OA) as one of several viable techniques.
from bs-roformer.
@Psarpei 512 is just a lot more common. Also torch istft and stft is slow so I suggest to not make it slower with non power of 2 values.
from bs-roformer.
Okay thanks for your answer :) but then there is the problem that the resulting audio length will not match the original one. What is your suggestion to handle that?
from bs-roformer.
Not all lengths are compatible. Check the length of the output you are getting and use that as the input length.
from bs-roformer.
but in that way I loose information at the end of the audio, how do you avoid that using this approach ?
from bs-roformer.
okay thanks :)
from bs-roformer.
Related Issues (20)
- MelBand doesn't work with stereo HOT 7
- Hidden dim in mask estimation module HOT 5
- Removed
- How to use it for audio source separation? HOT 2
- MLP design in MaskEstimator HOT 7
- Hardly to train with 8s length audio for batch size of 2 HOT 6
- Cut frequencies at half of the Nyquist in the MelBand model HOT 7
- Potential bug with `num_stems > 1` HOT 3
- Feature request: decouple the loss function of the forward function
- Problem with DataParallel HOT 5
- MelRoformer parameters from paper HOT 16
- Gates in Attention module of bs_roformer.py HOT 5
- Linear Attention temperature initialization HOT 1
- Flash attention error in Linear Attention layer HOT 1
- Reproduce the results from the paper HOT 1
- Linear Attention
- Input tensor size HOT 1
- Flash Attention support HOT 2
- [bad assertion] strange bottleneck performance HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from bs-roformer.