issues Search Results · repo:csteinmetz1/auraloss language:Python
Filter by
37 results
(71 ms)37 results
incsteinmetz1/auraloss (press backspace or delete to remove)Hi,
I ve found a simple way to objectively measure bleed and fullness in context of music source separation that I think
could be useful as I haven t seen any existing objective metric doing this, while ...
jarredou
- 3
- Opened on Oct 28, 2024
- #79
First of all, thanks a lot for writing and maintaining auraloss -- it is great to have a common package for these
functions!
auraloss seems to contain reasonable type annotations, at least for a certain ...
bluenote10
- Opened on Oct 15, 2024
- #77
Hello, thank you for your work, I m looking forward to use it in my studies. I have a short question, I don t have much
experience in that filed, so I don t fully understand how audio should be preprocessed ...
VlaDanilov
- Opened on Feb 22, 2024
- #73
import torch
import auraloss
mrstft = auraloss.freq.MultiResolutionSTFTLoss(reduction= none )
input = torch.rand(8,1,44100)
target = torch.rand(8,1,44100)
loss = mrstft(input, target)
print(loss)
print(loss.shape) ...
turian
- 7
- Opened on Dec 20, 2023
- #69
Dear author, Thank you very much for this cool and useful library. However the implementation of the SI-SDR and SD-SDR
time domain metrics looks very similar to me, am I missing something?
Chutlhu
- Opened on Dec 19, 2023
- #67
With the rise of fast vector databases for doing approximate nearest neighbors (FLANN, annoy, chroma, milvius, weaviate,
etc.), it becomes increasingly useful to have vectorial representations of audio ...
- 2
- Opened on Nov 20, 2023
- #66
Hello, First of all, thanks for the very useful library.
I found that the additional epsilon term is missing in auraloss/freq.py line 47-48 (torch.log). This part sometimes
causes nan gradient. I modified ...
dlfqhsdugod1106
- Opened on Aug 21, 2023
- #63
Hi!
As recommended by Välimäki et al., a pre-emphasis filter could be applied before applying ESR loss. A
auraloss.perceptual.FIRFilter instance, however, cannot be successfully called when the PyTorch ...
int0thewind
- 2
- Opened on Aug 1, 2023
- #62
From Zach: pass in different mel-bin sizes for the multi-resolution STFT loss in auraloss. The new Improved RVQGAN paper
shows that to be necessary.
image https://arxiv.org/abs/2306.06546
csteinmetz1
- Opened on Jul 12, 2023
- #61
Hi!
I tried to get the compressor example up and running and, in the process, migrated it as best I can to lightning 2.0.
There were several breaking changes, and as I ve never used lightning before and ...
mikesol
- Opened on May 31, 2023
- #60
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Restrict your search to the title by using the in:title qualifier.