README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - hearing loss
  - challenge
  - signal processing
  - source separation
  - audio
  - audio-to-audio
  - NonCausal

Cadenza Challenge: CAD2-Task1

A NonCausal Cello/Others separation model for the CAD2-Task2 baseline system.

• Architecture: ConvTasNet (Kaituo XU) with multichannel support (Alexandre Defossez).
• Parameters:
  • B: 256
  • C: 2
  • H: 512
  • L: 20
  • N: 256
  • P: 3
  • R: 3
  • X: 8
  • audio_channels: 2
  • causal: false
  • mask_nonlinear: relu
  • norm_type: gLN
• training:
  • sample_rate: 44100
  • samples_per_track: 64
  • segment: 5.0
  • aggregate: 2
  • batch_size: 4
  • early_stop: true
  • epochs: 200

Dataset

The model was trained using EnsembleSet and CadenzaWoodwind datasets.

How to use

from tasnet import ConvTasNetStereo

model = ConvTasNetStereo.from_pretrained(
    "cadenzachallenge/ConvTasNet_Cello_NonCausal"
).cpu()