ModelAufgelistetExtern

Roformer SpeechSep

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

Quellehuggingface.co/AliceN/Roformer-SpeechSep/tree/4d3cec9877105757ddb92b423054aa7758092804

ArtModellVersionRevision 4d3cec9CBewertung

Modellquelle

Art: Modell
Dateigröße: 97,6–415 MB
Version: vRevision 4d3cec9
Aktualisiert: 30. Okt. 2026
Downloads: 0
Quelle: Hugging Face

Quellenbeschreibung

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

Quellen

1 Quelle

Hugging FacePrimärVersion 4d3cec9877105757ddb92b423054aa7758092804

huggingface.co/AliceN/Roformer-SpeechSep/tree/4d3cec9877105757ddb92b423054aa7758092804

Verifiziert 30. Okt.

Download files

Repository files

File inventory only; completeness is unverified.

Modellartefakte

2 Artefakte

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

Quellenauszüge

3 Auszüge

Readme14. Aug.huggingface.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. Okt.huggingface.co/AliceN/Roformer-SpeechSep

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

Note14. Aug.huggingface.co/AliceN/Roformer-SpeechSep

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