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...
Source du modèle
- Type
- Other
- Taille du fichier
- 102 MB
- Version
- vRevision 9adc957
- Mis à jour
- 19 oct. 2026
- Téléchargements
- 20
- Source
- Hugging Face
Description de la source
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.
Sources
1 source
Sources
1 sourceVérifié 19 oct.
Artefacts du modèle
2 artefacts
Artefacts du modèle
2 artefactsExtraits de sources
3 extraits
Extraits de sources
3 extraits--- 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
