Model card
VITS.
Kakaoopen-sourceN/A paramsTTS
VITS: end-to-end TTS with conditional VAE and adversarial training. ICML 2021.
§ 01 · Benchmarks
Every benchmark VITS has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | VCTK | Speech · Text-to-Speech | mos | 4.2% | #2 | 2021-06-11 | source ↗ |
| 02 | LJ Speech | Speech · Text-to-Speech | mos | 4.4% | #3 | 2021-06-11 | source ↗ |
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.
§ 03 · Papers
1 paper with results for VITS.
- 2021-06-11· Speech· 2 results
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
2
results
2 of 2 rows marked verified.