pytorch / pytorch/audio

Envnet model and related transforms

Open
#92 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.9k
Forks
798
Avg merge
58m
Merged PRs (30d)
3

Description

Hey,

I'm implementing EnvNet with ESC50 dataset with pytorch, it works great, but I would like to pull it into torchaudio.
So far I'm using the utils from bc_learning , what would be the best way to put this utils in torch audio ? should I rewrite the utils to be full pytorch or leave it in numpy (as in torchvision, the PIL Image in transforms.py)

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the referenced bc_learning utils.py and comparing its EnvNet and ESC50 data transforms with torchaudio's existing transform conventions. The issue does not identify torchaudio files, tests, an accepted NumPy-versus-PyTorch design, or a clear completion criterion, so the scope needs maintainer clarification before implementation.

Written by the indexing model from the issue text.

Assessment

Tech stack
numpy, python, pytorch
Domain
audio-video-rtc, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.