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-0.1.0.tar.gz (314.5 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-0.1.0-py3-none-any.whl (11.2 kB view details)

Uploaded Python 3

File details

Details for the file hs_tasnet-0.1.0.tar.gz.

File metadata

  • Download URL: hs_tasnet-0.1.0.tar.gz
  • Upload date:
  • Size: 314.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.23

File hashes

Hashes for hs_tasnet-0.1.0.tar.gz
Algorithm Hash digest
SHA256 38e0d82f42c0a3f9a389a5db2fb19d58ac07bfeb4b7f408c3e1460807e7fc476
MD5 8486d359fddb307bedf4b28b356ebb4c
BLAKE2b-256 050108c617beebfd41103198bd925632a44b4724b4e74031a54b86b7a3ecddcf

See more details on using hashes here.

File details

Details for the file hs_tasnet-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: hs_tasnet-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 11.2 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-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2a29c765e9c5a7083bc5e5adf9ebb8c843f9c6f5a21ecc4e5ff081b25dba5936
MD5 bd2c9f1484dc87dbf584bac40ff427fd
BLAKE2b-256 1609100b7d864fed730fa610d877d38b9c23679a4a6f22d445d4c9641f41a3de

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