Codesota · Models · YourTTSEdresson Casanova et al.1 results · 1 benchmarks
Model card

YourTTS.

Edresson Casanova et al.open-sourceUnknown paramsVITS-based + speaker conditioning

YourTTS: zero-shot multi-speaker TTS based on VITS. ICML 2022.

§ 01 · Benchmarks

Every benchmark YourTTS has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01VCTKSpeech · Text-to-Speechmos4.1%#6/62022-02-08source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where YourTTS actually performs.

Speech
1
benchmark
avg rank #6.0
§ 03 · Papers

1 paper with results for YourTTS.

  1. 2022-02-08· Speech· 1 result

    YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

§ 05 · Sources & freshness

Where these numbers come from.

arxiv
1
result
1 of 1 rows marked verified.