Pith. sign in

For our first model, we fine- tuned XTTS-v2 using the SRG and STT4SG-350 data mix

Model Training As a baseline, we fine-tuned the pre-trained XTTS-v2 [4] on the STT4SG-350 data, which consists of 343 hours of training data, we refer to this model as Baseline

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Voice Adaptation for Swiss German

cs.CL · 2025-05-28 · conditional · novelty 5.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Voice Adaptation for Swiss German cs.CL · 2025-05-28 · conditional · none · ref 3

    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.