| language: | |
| - en | |
| license: apache-2.0 | |
| tags: | |
| - hearing loss | |
| - challenge | |
| - signal processing | |
| - source separation | |
| - audio | |
| - audio-to-audio | |
| - Causal | |
| # Cadenza Challenge: CAD2-Task1 | |
| A Causal Sax/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: true | |
| * mask_nonlinear: relu | |
| * norm_type: cLN | |
| * 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_Sax_Causal" | |
| ).cpu() | |
| ``` | |