Aller au contenu
ModelPrésentéExterne
Browse files

Roformer SpeechSep

Specially trained to separate the speaker's voice from background music that contains vocals.

Sourcehuggingface.co/AliceN/Roformer-SpeechSep/tree/4d3cec9877105757ddb92b423054aa7758092804
TypeModèleVersionRevision 4d3cec9CClasse

Source du modèle

Type
Modèle
Taille du fichier
97,6–415 MB
Version
vRevision 4d3cec9
Mis à jour
30 oct. 2026
Téléchargements
0
Source
Hugging Face

Description de la source

Specially trained to separate the speaker's voice from background music that contains vocals.

Sources

1 source
Hugging FacePrincipalVersion 4d3cec9877105757ddb92b423054aa7758092804
huggingface.co/AliceN/Roformer-SpeechSep/tree/4d3cec9877105757ddb92b423054aa7758092804

Vérifié 30 oct.

Download files

Repository files

File inventory only; completeness is unverified.

Artefacts du modèle

2 artefacts

speech_bs_roformer_AliceN_sdr_20.4440.ckpt

ckpt · 97,6 MB · SHA-256 f4300ef0b230…41ae · Hugging Face

Download file

speech_mel_roformer_AliceN_sdr_16.5716.ckpt

ckpt · 415 MB · SHA-256 f2bd58827042…8137 · Hugging Face

Download file

Extraits de sources

3 extraits
Readme14 aoûthuggingface.co/AliceN/Roformer-SpeechSep

--- pipeline_tag: audio-to-audio tags: - roformer - speech --- Specially trained to separate the speaker's voice from background music that contains vocals.

Note30 oct.huggingface.co/AliceN/Roformer-SpeechSep

Source context: 0 downloads · 4 likes · Pipeline audio-to-audio · Repo AliceN/Roformer-SpeechSep

Note14 aoûthuggingface.co/AliceN/Roformer-SpeechSep

Source context: 0 downloads · 1 likes · Pipeline audio-to-audio · Repo AliceN/Roformer-SpeechSep