Saltar al contenido
ModelPublicadoExterno
Descargar

ConvTasNet Viola NonCausal

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

Fuentehuggingface.co/cadenzachallenge/ConvTasNet_Viola_NonCausal/tree/82094d81b55a70dc4c3888f1a846b29d689f2a2b
TipoOtherVersiónRevision 82094d8

Fuente del modelo

Tipo
Other
Tamaño del archivo
25,2 MB
Versión
vRevision 82094d8
Actualizado
18 sept 2026
Descargas
5
Tareas
Audio
Fuente
Hugging Face

Descripción de la fuente

Cadenza Challenge: CAD2-Task1

A NonCausal Viola/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_Viola_NonCausal"
).cpu()

Fuentes

1 fuente
Hugging FacePrincipalVersión 82094d81b55a70dc4c3888f1a846b29d689f2a2b
huggingface.co/cadenzachallenge/ConvTasNet_Viola_NonCausal/tree/82094d81b55a70dc4c3888f1a846b29d689f2a2b

Verificado 18 sept

Artefactos del modelo

1 artefacto

model.safetensors

safetensors · 25,2 MB · SHA-256 2bd3f78659d0…9eae · Hugging Face

Descargar

Extractos de fuentes

2 extractos
Readme18 septhuggingface.co/cadenzachallenge/ConvTasNet_Viola_NonCausal

--- 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 Viola/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_Viola_NonCausal" ).cpu() ```

Note18 septhuggingface.co/cadenzachallenge/ConvTasNet_Viola_NonCausal

Source context: 5 downloads · 0 likes · Pipeline audio-to-audio · Library transformers · Repo cadenzachallenge/ConvTasNet_Viola_NonCausal