ClonEval: An Open Voice Cloning Benchmark
- AuLLM
Main:3 Pages
1 Figures
3 Tables
Appendix:2 Pages
Abstract
We present a novel benchmark for voice cloning text-to-speech models. The benchmark consists of an evaluation protocol, an open-source library for assessing the performance of voice cloning models, and an accompanying leaderboard. The paper discusses design considerations and presents a detailed description of the evaluation procedure. The usage of the software library is explained, along with the organization of results on the leaderboard.
View on arXivComments on this paper
