nomadkaraoke/python-audio-separator

Issues

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

  #90 opened 2 months ago by ybwai
  14

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

  #79 opened 3 months ago by zhyqieqie
  1

• Request to add Band-split RNN model!

  #75 opened 4 months ago by piwawa
  2

• UVR-DeEcho-DeReverb not really working (Amazon Linux)

  #45 opened 7 months ago by venkat-sf
  4

• Demucs models require Python version 3.10 or newer.

  #83 opened 2 months ago by zhyqieqie
  2

• Cannot use mp3 file that UVR was working with.

  #77 opened 4 months ago by drakon660
  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 2 months ago by Lixi20
  2

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

  #86 opened 2 months ago by Lixi20
  1

• Feature request: download model only

  #92 opened 2 months ago by incidentist
  2

• Support custom file names for primary and secondary stem

  #89 opened 2 months ago by JackismyShephard
  4

• Some VR Arch models show the error: librosa.util.exceptions.ParameterError: Audio buffer is not finite everywhere

  #52 opened 2 months ago by Eddycrack864
  5

• "CUDA_PATH is set but CUDA wasnt able to be loaded" error despite successful --env_info test

  #70 opened 4 months ago by jet082
  3

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

  #73 opened 3 months ago by jet082
  16

• Recommend a model

  #78 opened 3 months ago by joseph16388
  7

• GitHub Discussions ?

  #80 opened 3 months ago by l2aelba
  1

• Failed to load library libonnxruntime_providers_cuda.

  #31 opened 9 months ago by yassinebelatar
  3

• add model_bs_roformer model support

  #66 opened 4 months ago by superchaos
  6

• fast guitar processing mode

  #71 opened 4 months ago by negeevmaks
  5

• Randomly raising "librosa ParameterError: Audio buffer is not finite everywhere (cutting wav files)" 1 out 5 generations

  #57 opened 6 months ago by smartinezbragado
  13

• karaoke model sometimes cuts off the climax part of the song

  #68 opened 4 months ago by yuchenooooooo
  3

• Cannot install the latest PyPI package

  #54 opened 4 months ago by Faultiness
  11

• 在分离带有二胡声的音频中，二胡声分离不出去，比如兰亭序，这该采用什么模型，有那种直接全部分离出去的模型吗？

  #46 opened 4 months ago by ymmbb8882ymmbb
  2

• Large instrumental bleedthrough in some vocal tracks

  #49 opened 4 months ago by masonasons
  3

• Add a model

  #58 opened 4 months ago by shirounanashi
  5

• Using the same model and configuration, but the results are much worse than UVR5.6

  #59 opened 4 months ago by yuchenooooooo
  16

• cuda12.0 is available?

  #69 opened 4 months ago by chicumt
  2

• Can't load `htdemucs_ft.yaml`

  #67 opened 5 months ago by piwawa
  1

• Incorrect model path when loading model data from .yaml

  #64 opened 5 months ago by helloimmatt
  1

• Fails to run when segment_size is set to anything except 256 in mdx_params of Separator

  #51 opened 5 months ago by CarpetBook
  7

• How to assign ffmpeg's encoding parameters?

  #61 opened 5 months ago by owen8849
  2

• Reverb_HQ_By_FoxJoy.onnx cannot work, I cannot figure out what happened here, please help.

  #62 opened 6 months ago by XeoOuYang
  2

• New version with a buggy demucs_separator

  #60 opened 6 months ago by GeleiaComPepino
  4

• Error writing big Audio files

  #53 opened 6 months ago by iampickle
  2

• Implement support for checkpoint models (e.g. "MDX23C-8KFFT-InstVoc_HQ_2.ckpt")

  #42 opened 6 months ago by ajayarora1235
  4

• Issue with Files Being Overwritten When Batch Processing Audio Files

  #48 opened 6 months ago by soutlu
  2

• audio-separator: error: unrecognized arguments: --model_name=UVR_MDXNET_KARA

  #47 opened 7 months ago by jonata
  4

• GPU not being used on Colab

  #43 opened 7 months ago by ajayarora1235
  4

• Separator terminated with "Killed" message (Out of memory / OOM error on Linux)

  #44 opened 7 months ago by Tiaranso
  5

• How to increase speed?

  #32 opened 7 months ago by yassinebelatar
  20

• issues pip isntalling in colab (samplerate)

  #40 opened 7 months ago by ajayarora1235
  2

• Problem with installing models

  #39 opened 8 months ago by crexlight
  3

• some popping sound occurred

  #29 opened 8 months ago by mc261670164
  12

• No hardware acceleration could be configured, running in CPU mode

  #33 opened 8 months ago by quanpy
  5

• Supporting VR Architecture models like HP5

  #37 opened 8 months ago by KevinWang676
  6

• UnboundLocalError: local variable 'h' referenced before assignment

  #38 opened 8 months ago by GoombaFCU
  1

• Some errors popping up, Process seems slow.!!

  #34 opened 8 months ago by Rahat47
  3

• MDX23C-8KFFT-InstVoc_HQ_2.ckpt model

  #30 opened 9 months ago by yassinebelatar
  1

• AttributeError: module 'onnxruntime' has no attribute 'get_device'

  #27 opened 9 months ago by tobq
  2

• Error Installing audio-separator with GPU Support: Dependency Conflicts and CUDA Library Issue

  #25 opened 9 months ago by tobq
  3

• run under cuda

  #26 opened 9 months ago by ischeck
  1