Skip to main content

AUV

Teaching Audio Universal Vector Quantization with Single Nested Codebook

python arXiv demo

Setup

pip install auv
wget https://huggingface.co/SWivid/AUV/resolve/main/auv.pt

Inference

Command line usage, reconstruct all .wav files under the input-dir and write to the output-dir:

auv-infer --input-dir INPUT_WAV_DIR --output-dir OUTPUT_WAV_DIR --ckpt CKPT_PATH
# if torch.bfloat16 inference: --bf16
# if need to assign gpu: --device cuda:0

Python script usage see src/auv/infer.py.

Release files for auv 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for auv 0.1.1
File Size Uploaded
auv-0.1.1.tar.gz 14.1 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for auv 0.1.1
File Interpreter ABI Platform
auv-0.1.1-py3-none-any.whl Python 3 none any Details

Total release size: 27.4 kB

Release files / auv-0.1.1.tar.gz

Download URL auv-0.1.1.tar.gz
Size 14.1 kB
Tags Source
SHA-256 checksum
How to use checksums
a5ee5303c94b491b34efc1b8a3e8b84be15075c3f9ed33973861113e65dfce75
BLAKE2b-256 checksum
How to use checksums
db4643f6ca822209bd1dadaa3070ca33d64210ff71fedb3defeed8cd264aad0a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 11, 2025.

Transparency log

Release files / auv-0.1.1-py3-none-any.whl

Download URL auv-0.1.1-py3-none-any.whl
Size 13.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
5da06a15c440bdeb2664e1da16494d2af4e6c60cc4bb51317609332919cceb14
BLAKE2b-256 checksum
How to use checksums
82d16e2e0649ee5d1047fbcd90d2c8be5fc1449bdd08f2e68a2bddaf84dc547d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 11, 2025.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.1 This release

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page