nomadkaraoke/python-audio-separator

Issues

• [Bug]: "Unsupported Model File" error for HTDemucs_6s

  #161 opened a month ago by IneffableBunch
  2

• [Feature]: Realtime Decode MDX for Online Karaoke Plugin

  #160 opened a month ago by GenzPN
  1

• The size of tensor a (352768) must match the size of tensor b (352800) at non-singleton dimension 1

  #113 opened 4 months ago by Eddycrack864
  5

• [Bug]: Insufficient memory when processing large files

  #158 opened a month ago by echoIIImk2
  0

• Please support python3.9

  #156 opened 2 months ago by MonolithFoundation
  9

• Hi， is that support Chinese drama background music seperate?

  #155 opened 2 months ago by MonolithFoundation
  1

• Problem with noise after audio separation

  #151 opened 2 months ago by kbuwel
  1

• Support custom file names for primary and secondary stem

  #89 opened 6 months ago by JackismyShephard
  7

• New model `Lew's Vocal Enhancer`

  #150 opened 2 months ago by Bebra777228
  0

• [Bug]: installing on python > 3.10 on Windows requires Visual Studio build tools

  #149 opened 2 months ago by JackismyShephard
  0

• [Bug]: using specific model in docker not working

  #147 opened 2 months ago by acimail01
  0

• New Roformer Models

  #145 opened 2 months ago by Bebra777228
  5

• Resolving ONNX Runtime CUDA Provider Error in Google Colab

  #142 opened 2 months ago by Bebra777228
  1

• Killed for the long recording

  #120 opened 3 months ago by Ylw2014
  1

• Roformer Models STILL broken on Windows - Tested on Multiple Computers

  #116 opened 3 months ago by jet082
  2

• Module error

  #131 opened 3 months ago by kbuwel
  1

• Problem recognizing gpu but only working with cpu

  #137 opened 2 months ago by kbuwel
  1

• Renaming files within `audio-separator`

  #128 opened 2 months ago by Bebra777228
  4

• Minimum and maximum values of architectural parameters

  #138 opened 2 months ago by Bebra777228
  2

• [Bug]: CLI unable to work with parenthesis filenames: mdxc self.primary_stem_output_path

  #140 opened 2 months ago by StarMariner
  2

• Separate voices from a vocal track?

  #121 opened 2 months ago by lyubomyr-shaydariv
  4

• Best Settings

  #123 opened 3 months ago by Bebra777228
  2

• Model Suggestions

  #136 opened 3 months ago by shreeshailgan
  2

• There is a performance difference between audio-separator and UVR_v5.6.0_setup_10_14.exe

  #129 opened 3 months ago by OneSeven
  9

• File Formats

  #122 opened 3 months ago by Bebra777228
  2

• Intermittent error loading mel_band_roformer

  #119 opened 3 months ago by ybwai
  1

• Is it normal that 3 minute track takes 7 minutes to separate (Apple Silicon, no GPU)?

  #106 opened 4 months ago by caner-cetin
  7

• VR HP models causing OOM with 12gb VRAM

  #109 opened 4 months ago by kikoferrer
  4

• The new Bandit v2 model

  #112 opened 4 months ago by Bebra777228
  2

• I didn't quite understand the instructions for usage

  #111 opened 4 months ago by Bebra777228
  5

• Request support for new model：denoise_mel_band_roformer_aufr33_aggr_sdr_27.9768.ckpt 、denoise_mel_band_roformer_aufr33_sdr_27.9959.ckpt ...

  #99 opened 4 months ago by changqingonly
  2

• Cannot use mp3 file that UVR was working with.

  #77 opened 4 months ago by drakon660
  3

• The processing results of the UVR-DeNoise. pth model are different from those of UVR5 client.

  #79 opened 4 months ago by zhyqieqie
  3

• Regarding the Mel RoFormer models not using CUDA in latest audio-separator version

  #97 opened 4 months ago by HitRoxxx
  8

• 哪个模型提取音乐中的人声效果最好？

  #100 opened 4 months ago by Garyguhaifeng
  10

• Why is there no sound sometimes when using the 5_HP-Karaoke-UVR.pth model?

  #98 opened 4 months ago by Lixi20
  4

• mdxc_separator.py: RuntimeError

  #96 opened 4 months ago by Oefuli
  9

• MP3 output defaults to 128kbps

  #103 opened 4 months ago by empz
  8

• Roformer Models Not Running on GPU. Other models fine. Roformer models run on GPU on UVR5.

  #73 opened 6 months ago by jet082
  17

• Disable Normalization

  #94 opened 5 months ago by dj-nuo
  1

• Utilising ANE (Apple Neural Engine) for inference

  #93 opened 5 months ago by dj-nuo
  3

• can't get .pth and .ckpt models working

  #90 opened 6 months ago by ybwai
  14

• Request to add Band-split RNN model!

  #75 opened 7 months ago by piwawa
  2

• Demucs models require Python version 3.10 or newer.

  #83 opened 6 months ago by zhyqieqie
  2

• ValueError: Unsupported Model File: parameters for MD5 hash dac7f142d5adf52ee84c1e900a3c2725 could not be found in UVR model data file for MDX or VR arc

  #85 opened 6 months ago by Lixi20
  2

• AttributeError: 'VRSeparator' object has no attribute 'arch_name'

  #86 opened 6 months ago by Lixi20
  1

• Feature request: download model only

  #92 opened 6 months ago by incidentist
  2

• Recommend a model

  #78 opened 6 months ago by joseph16388
  7

• GitHub Discussions ?

  #80 opened 6 months ago by l2aelba
  1

• fast guitar processing mode

  #71 opened 8 months ago by negeevmaks
  5