ConvTasNet_Lyrics_NonCausal

cadenzachallenge/ConvTasNet_Lyrics_NonCausal

ConvTasNet_Lyrics_NonCausal is a audio-to-audio model from cadenzachallenge. Use it for the audio-to-audio task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

A NonCausal Lyrics/Accompaniment separation model for the CAD2-Task1 baseline system.

Downloads · 30 days

0% of all-time downloads

All-time downloads

3.8K

Public

Parameters

10.8M

130 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin43.5 MB · 50%

At a glance

Task: Audio-to-Audio
Library: transformers
License: apache-2.0
Access: Public
Created: May 20, 2024
Updated: Jun 26, 2024
SHA: 96a3d103

Model card

From the Hugging Face model README

Cadenza Challenge: CAD2-Task1

A NonCausal Lyrics/Accompaniment separation model for the CAD2-Task1 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: 4
- X: 10
- 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 on the training split of the MUSDB18-HQ dataset.

How to use

from tasnet import ConvTasNetStereo

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

Results

Track	Vocals (SDR)	Accompaniment (SDR)
Al James - Schoolboy Facination	6.841	9.074
AM Contra - Heart Peripheral	6.948	14.105
Angels In Amplifiers - I'm Alright	7.358	10.859
Arise - Run Run Run	6.105	16.806
Ben Carrigan - We'll Talk About It All Tonight	2.853	10.181
BKS - Bulldozer	1.909	13.944
BKS - Too Much	8.615	13.212
Bobby Nobody - Stitch Up	7.948	12.685
Buitraker - Revo X	4.609	14.61
Carlos Gonzalez - A Place For Us	4.235	8.888
Cristina Vane - So Easy	8.759	13.639
Detsky Sad - Walkie Talkie	7.732	10.844
Enda Reilly - Cur An Long Ag Seol	9.603	13.723
Forkupines - Semantics	4.955	11.561
Georgia Wonder - Siren	4.124	8.578
Girls Under Glass - We Feel Alright	4.38	12.272
Hollow Ground - Ill Fate	7.046	16.299
James Elder & Mark M Thompson - The English Actor	4.694	9.638
Juliet's Rescue - Heartbeats	6.281	14.409
Little Chicago's Finest - My Own	6.313	6.603
Louis Cressy Band - Good Time	6.501	12.016
Lyndsey Ollard - Catching Up	9.18	12.116
M.E.R.C. Music - Knockout	6.619	8.507
Moosmusic - Big Dummy Shake	8.097	14.578
Motor Tapes - Shore	0.769	10.137
Mu - Too Bright	5.853	13.135
Nerve 9 - Pray For The Rain	6.425	14.427
PR - Happy Daze	0	51.092
PR - Oh No	0	9.021
Punkdisco - Oral Hygiene	5.725	17.681
Raft Monk - Tiring	2.378	9.244
Sambasevam Shanmugam - Kaathaadi	8.164	10.588
Secretariat - Borderline	5.522	10.817
Secretariat - Over The Top	7.859	14.996
Side Effects Project - Sing With Me	11.197	12.63
Signe Jakobsen - What Have You Done To Me	7.685	11.013
Skelpolu - Resurrection	0	7.603
Speak Softly - Broken Man	3.997	14.516
Speak Softly - Like Horses	6.462	9.426
The Doppler Shift - Atrophy	0.711	14.241
The Easton Ellises - Falcon 69	2.401	7.889
The Easton Ellises (Baumi) - SDRNR	1.479	7.948
The Long Wait - Dark Horses	6.53	12.661
The Mountaineering Club - Mallory	10.665	15.311
The Sunshine Garcia Band - For I Am The Moon	9.591	13.297
Timboz - Pony	4.025	14.271
Tom McKenzie - Directions	8.031	16.129
Triviul feat. The Fiend - Widow	7.061	8.168
We Fell From The Sky - Not You	3.862	11.685
Zeno - Signs	6.364	11.552
Total (median over frames, median over tracks)	6.338	12.194

Task: Audio-to-Audio
Library: transformers
License: apache-2.0
Languages: en
Created: May 20, 2024
Updated: Jun 26, 2024