Robust Speaker Cloning
Large artifacts for the companion GitHub repository. V2 trains a 6-layer robust speaker Transformer and telephone BWE front end while keeping CosyVoice2-0.5B frozen. On 21 paired real CosyVoice generations, ECAPA...
Modellquelle
- Art
- Other
- Dateigröße
- 102 MB
- Version
- vRevision 9adc957
- Aktualisiert
- 19. Okt. 2026
- Downloads
- 20
- Quelle
- Hugging Face
Quellenbeschreibung
Robust Speaker Cloning artifacts
Large artifacts for the companion GitHub repository. V2 trains a 6-layer robust speaker Transformer and telephone BWE front end while keeping CosyVoice2-0.5B frozen. On 21 paired real CosyVoice generations, ECAPA x-vector similarity was 0.6187 for V2 versus 0.5998 baseline (+0.0189 average). This small evaluation also contains negative HVAC and reverb deltas, so it is not a universal-improvement claim.
CosyVoice, CampPlus, ECAPA and AISHELL retain their upstream licenses.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 19. Okt.
Modellartefakte
2 Artefakte
Modellartefakte
2 ArtefakteQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- language: - zh tags: - text-to-speech - voice-cloning - cosyvoice - speaker-verification license: mit --- # Robust Speaker Cloning artifacts Large artifacts for the companion GitHub repository. V2 trains a 6-layer robust speaker Transformer and telephone BWE front end while keeping CosyVoice2-0.5B frozen. On 21 paired real CosyVoice generations, ECAPA x-vector similarity was 0.6187 for V2 versus 0.5998 baseline (+0.0189 average). This small evaluation also contains negative HVAC and reverb deltas, so it is not a universal-improvement claim. CosyVoice, CampPlus, ECAPA and AISHELL retain their upstream licenses.
Source context: 20 downloads · 0 likes · Pipeline text-to-speech · Library cosyvoice · Repo jatshi/robust-speaker-cloning
Source context: 106 downloads · 0 likes · Pipeline text-to-speech · Library cosyvoice · Repo jatshi/robust-speaker-cloning
