MVSEP Logo
  • Home
  • News
  • Plans
  • Demo
  • FAQ
  • Create Account
  • Login

MelBand Roformer (vocals, instrumental)

Алгоритм для разделения треков на вокальную и инструментальную части на базе нейронной сети MelBand Roformer. Нейронная сеть впервые предложена в статье "Mel-Band RoFormer for Music Source Separation" от группы ученых из компании ByteDance. Первые веса высокого качества в открытый доступ выложила Kimberley Jensen. Далее нейронная сеть с открытыми весами была немного изменена и дотренирована командой MVSep с целью улучшить метрики качества. Также имеются высококачественные веса, предоставленные: @Bas Curtiz, @unwa, @becruily и @gabox.

Таблица качества

Algorithm name Multisong dataset Synth dataset MDX23 Leaderboard
SDR Vocals SDR Instrumental SDR Vocals SDR Instrumental SDR Vocals
MelBand Roformer (Kimberley Jensen) 11.01 17.32 12.68 12.38 11.543
MelBand Roformer (ver. 2024.08) 11.17 17.48 13.34 13.05 ---
Bas Curtiz edition 11.18 17.49 13.89 13.60 ---
unwa Instrumental v1 10.24 16.54 12.25 11.95 ---
unwa Instrumental v1e
Note: Max instrum fullness, but noisy
10.05 16.36 --- --- ---
unwa big beta v5e
Note: Max vocals fullness, but noisy
10.59 16.89 --- --- ---
MelBand Roformer (ver. 2024.10) 11.28 17.59 13.89 13.59 ---
becruily instrum max fullness 
Note: Max instrum fullness, but noisy
10.16 16.47 --- --- ---
becruily vocals max fullness
Note: Max vocals fullness, but noisy
10.55 16.86 --- --- ---
unwa Instrumental v1e plus
Note: Max instrum fullness, but noisy
10.33 16.64 --- --- ---
gabox Instrumental v7
Note: Max instrum fullness, but noisy
10.32 16.63 --- --- ---

Детальная статистика на Multisong датасете:

Модель Vocals fullness Vocals bleedless  Vocals SDR Vocals L1Freq Instrum fullness Instrum bleedless  Instrum SDR Instrum L1Freq
MelBand Roformer (Kimberley Jensen) 16.66 36.51 11.01 38.96 27.71 46.72 17.32 39.77
MelBand Roformer (ver. 2024.08) 16.39 39.13 11.18 39.26 27.74 47.07 17.49 40.16
Bas Curtiz edition 16.30 38.94 11.18 39.18 27.49 47.00 17.49 40.15
MelBand Roformer (ver. 2024.10) 16.92 37.78 11.28 39.41 27.71 47.29 17.59 40.29
unwa Instrumental v1 (SDR vocals: 10.24, SDR instrum: 16.54) 15.89 27.48 10.24 36.06 35.44 38.02 16.55 38.67
unwa Instrumental v1e (SDR vocals: 10.05, SDR instrum: 16.36) 14.67 26.83 10.06 34.37 38.85 35.68 16.37 38.31
unwa big beta v5e (SDR vocals: 10.59, SDR instrum: 16.89) 20.78 32.02 10.59 38.53 25.65 45.90 16.90 37.31
becruily instrum high fullness (SDR instrum: 16.47) 15.76 30.15 10.16 35.84 33.93 40.55 16.47 38.86
becruily vocals high fullness (SDR vocals: 10.55) 20.72 31.25 10.55 38.84 28.28 40.85 16.86 38.24
unwa Instrumental v1e plus (SDR vocals: 10.33, SDR instrum: 16.64) 14.96 31.89 10.33 35.76 36.20 38.57 16.64 39.04
gabox Instrumental v7 (SDR vocals: 10.32, SDR instrum: 16.63) 16.25 27.28 10.32 36.85 29.34 45.06 16.63 38.70
🗎 Copy link

MVSEP Logo

turbo@mvsep.com

Advanced features

Quality Checker

Algorithms

Full API Documentation

Company

Privacy Policy

Terms & Conditions

Refund Policy

Cookie Notice

Extra

Help us translate!

Help us promote!