Fine-tuning XTTS-v2 on about 5,000 hours of weakly labeled Swiss podcast audio produces a voice adaptation model that renders Standard German text in seven Swiss German dialect regions with near-reference quality in human and automated tests.
The learning rate was changed to 6e-5 from the original 5e-5 due to internal tests and listening to the generated audio files
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Voice Adaptation for Swiss German
Fine-tuning XTTS-v2 on about 5,000 hours of weakly labeled Swiss podcast audio produces a voice adaptation model that renders Standard German text in seven Swiss German dialect regions with near-reference quality in human and automated tests.