marl/openl3

Issues

• Feature Request: Integration with Ollama

  #97 opened 4 months ago by gwpl
  0

• Extract activation from lower audio layers

  #90 opened 7 months ago by seunggookim
  1

• error when initializing the model

  #96 opened a year ago by sivannavis
  1

• Error installing openl3 on Win64 with Python 3.10

  #94 opened 2 years ago by rjungbeck
  6

• Dependency conflict with Tensorflow 2.5.x

  #82 opened 2 years ago by jonnor
  0

• m1 macos installation problem

  #89 opened 3 years ago by yy945635407
  4

• Example of fine-tuning the audio sub-network.

  #91 opened 3 years ago by mattiacampana
  1

• [DOC] Tutorial could include a classification example

  #41 opened 5 years ago by bmcfee
  4

• Clarification on input representation

  #92 opened 3 years ago by alisonbma
  0

• Breaks with librosa 0.9.x

  #85 opened 3 years ago by jonnor
  0

• Export OpenL3 as TF/TF-Lite model

  #87 opened 3 years ago by mattiacampana
  0

• Numerical errors in hop_len due to rounding

  #81 opened 4 years ago by turian
  0

• Add note to docs about embeddings changing after tensorflow 2 / kapre + librosa upgrade

  #80 opened 4 years ago by beasteers
  0

• Migrate from Travis CI to GitHub Actions

  #79 opened 4 years ago by auroracramer
  0

• Add Action for running US8K benchmark

  #78 opened 4 years ago by auroracramer
  0

• Make linear frontend consistent with mel

  #77 opened 4 years ago by auroracramer
  0

• Coveralls not triggered on successful Travis build

  #76 opened 4 years ago by auroracramer
  0

• Replace resampy with pysox for audio resampling

  #49 opened 5 years ago by justinsalamon
  0

• Add function to API for loading custom model weights

  #69 opened 4 years ago by auroracramer
  1

• Drop support for Python 2.x

  #45 opened 4 years ago by auroracramer
  2

• Refactor code and models to support TF 2.x and tf.keras

  #46 opened 4 years ago by auroracramer
  16

• Drop support for Python <=3.5 and add support for Python 3.7, and 3.8

  #52 opened 4 years ago by auroracramer
  1

• error in the documentation of the image embedding sizes ?

  #60 opened 4 years ago by adrienchaton
  3

• API docs broken

  #71 opened 4 years ago by auroracramer
  1

• skimage submodules not imported correctly, regression tests fail

  #73 opened 4 years ago by auroracramer
  7

• Expected new release

  #67 opened 4 years ago by JNaranjo-Alcazar
  1

• git clone pulls weight files as well by default

  #70 opened 4 years ago by beasteers
  1

• Pretrained fusion layers

  #58 opened 4 years ago by adrienchaton
  2

• urllib.error.URLError: <urlopen error [WinError 10060]

  #59 opened 4 years ago by a-flying-crow
  0

• PyTorch models

  #35 opened 5 years ago by sainathadapa
  14

• cant isntall openl3 in my ubuntu system

  #57 opened 4 years ago by LongYin-Guo
  1

• Bug in CLI centering?

  #56 opened 4 years ago by turian
  1

• pip error when installing

  #50 opened 5 years ago by hugofloresgarcia
  4

• Pytorch version

  #54 opened 4 years ago by turian
  0

• path of openl3_audio_linear_music-v0_2_0.h5.gz not exists

  #53 opened 4 years ago by jammyWolf
  1

• Disable logging

  #51 opened 4 years ago by turian
  1

• Failed to construct network. Tried both Tensorflow 2.0.0 and 1.9.5, Keras2.3.1 and 2.2.5

  #43 opened 5 years ago by zhao-shuyang
  2

• Explicitly require tensorflow < 2.0

  #42 opened 5 years ago by auroracramer
  1

• tensorflow 2.1 doesn't require separate pip installes for gpu and cpu

  #39 opened 5 years ago by faroit
  8

• Unable to find models

  #40 opened 5 years ago by happypanda5
  3

• Implement image embedding API

  #19 opened 5 years ago by auroracramer
  26

• Add batch processing mode

  #26 opened 5 years ago by auroracramer
  10

• memory continue growing when get_embedding

  #38 opened 5 years ago by jiqiujia
  1

• Streaming / real-time usage?

  #36 opened 5 years ago by jonnor
  1

• conda-forge packaging?

  #30 opened 6 years ago by bmcfee
  4

• API reference in documentation missing

  #28 opened 6 years ago by jonnor
  4

• About pre-trained model and paper

  #21 opened 6 years ago by bearsroom
  2

• Make an object-oriented interface for embedding models

  #22 opened 6 years ago by auroracramer
  4

• [Q] Audio chunk duration greater than 1 second

  #24 opened 6 years ago by bbruhh
  1

• why I can't install openl3 now？

  #20 opened 6 years ago by zsmj610
  2