Skip to content

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 

Repository files navigation

Kavya Gupta

Unified multitask audio modeling — one language model, many audio tasks.

Independent researcher working toward a single framework that handles audio enhancement, separation, conversion and generation with shared weights, instead of maintaining a zoo of single-task models. I'm opinionated about three things, in order:

  • Consolidation — one model conditioned on a task, not ten networks to keep alive.
  • Reproducibility — seeds, from-scratch maths, and nothing to download to run the demos.
  • Honest evaluation — the comparison is the claim; a single averaged score hides more than it shows.

Featured projects

Two halves of the same thesis: a unified model, and the harness that keeps its claims honest. Both are small, dependency-light reference implementations meant to make the idea easy to read and reproduce.

Project What it is
audiomux One decoder-only autoregressive model over discrete audio tokens. A classical codec (mu-law + k-means VQ) turns a waveform into tokens; a reserved task tokenenhance, separate or generate — conditions the shared weights. Pure NumPy, with the forward and backward passes written by hand and checked against finite differences, so the test suite doubles as a correctness proof.
polyaudio A multitask audio evaluation suite. It drives the same model object across heterogeneous tasks (keyword spotting, language ID, tagging, valence regression, mini-ASR), scores each with the metric that task actually cares about, and prints them side by side against trivial baselines. NumPy-only, because it scores predictions — not a leaderboard number, a table.

The through-line

audiomux is the argument that one set of weights can do many audio tasks. polyaudio is the discipline that keeps that argument honest: if a unified model can't beat prior or majority on a task, the table says so plainly. Building both together is the point — a model is only as good as the comparison you're willing to show next to it.


Toolbox

Python NumPy pytest Ruff mypy uv TOML MIT License

From-scratch autoregressive decoders over discrete audio tokens · finite-difference gradient checks · declarative TOML evaluation suites · per-task metrics (WER, mAP, Pearson, accuracy) over a shared harness.


Currently

  • Growing audiomux from toy synthetic signals toward more realistic audio, keeping the plumbing and maths readable at every step.
  • Expanding polyaudio with more task kinds and baselines, so unified-model claims stay falsifiable.
  • Interested in: task-conditioned generation, discrete audio codecs, and evaluation that a skeptic would trust.

About

Profile README

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors