Skip to main content

HS TasNet

Project description

HS-TasNet (wip)

Implementation of HS-TasNet, "Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet", proposed by the research team at L-Acoustics

Install

$ pip install HS-TasNet

Usage

import torch

from hs_tasnet.hs_tasnet import HSTasNet

model = HSTasNet()

print(model.num_parameters) # 41694553 ~ 41M in paper

small_model = HSTasNet(small = True)

print(small_model.num_parameters) # 19666553 ~ 16M in paper

Sponsors

This open sourced work is sponsored by Sweet Spot

Citations

@misc{venkatesh2024realtimelowlatencymusicsource,
    title    = {Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet}, 
    author   = {Satvik Venkatesh and Arthur Benilov and Philip Coleman and Frederic Roskam},
    year     = {2024},
    eprint   = {2402.17701},
    archivePrefix = {arXiv},
    primaryClass = {eess.AS},
    url      = {https://arxiv.org/abs/2402.17701}, 
}

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

hs_tasnet-0.1.5.tar.gz (314.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

hs_tasnet-0.1.5-py3-none-any.whl (11.4 kB view details)

Uploaded Python 3

File details

Details for the file hs_tasnet-0.1.5.tar.gz.

File metadata

  • Download URL: hs_tasnet-0.1.5.tar.gz
  • Upload date:
  • Size: 314.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.23

File hashes

Hashes for hs_tasnet-0.1.5.tar.gz
Algorithm Hash digest
SHA256 c35bb70010da0f2496e623978673147665ad6aa69291ffd7aa44d9b3dcae0ebf
MD5 04ad8808e188efb5cb338375aa36c761
BLAKE2b-256 8c67245cb849c9d85ef184f04252042c25e0a8130ef0017872cbaf1483f5c3ea

See more details on using hashes here.

File details

Details for the file hs_tasnet-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: hs_tasnet-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 11.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.23

File hashes

Hashes for hs_tasnet-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 e392975f42ad59993e6c7de782e0c43731157e1891a255bf15697529626aa197
MD5 ad4beb5fb7e18f0349d0c055e2067726
BLAKE2b-256 14cf4ac3324da271c6bfb50a7e5869728a19a8669d47046926b121735035c0e0

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page