whatmodel.sh / tts / Tacotron 2 + HiFi-GAN (LJ Speech)

Tacotron 2 + HiFi-GAN (LJ Speech)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Tacotron 2 + HiFi-GAN (LJ Speech) is an open-weights text-to-speech model from VITS study (public implementations), released June 2021.

Catalogue identity notes

Exact ljspeech system in VITS Table 1; HiFi-GAN fine-tuning is a distinct vocoder configuration. Published implementation/checkpoint links in §3.4; no generic Tacotron or Glow-TTS score substitution.

23.4±20.6comparison only: no current run option verifiedfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

Score within the VITS 2021 LJ Speech human MOS comparison set only.

$ how it compares

Scored text-to-speech models released closest to Tacotron 2 + HiFi-GAN (LJ Speech), out of 148 with a score.

#modelscorewhereRAMreleased
81Azure Ameha Neural Microsoft50±16comparison only2021-10
82Azure Mekdes Neural Microsoft50±16comparison only2021-10
124VITS (VCTK multi-speaker) Kakao Enterprise (Jaehyeon Kim et al.)34±5local~0.2GB2021-06
135Glow-TTS + HiFi-GAN (VCTK, VITS study) VITS study (public implementations)28±6comparison only2021-06
142Tacotron 2 + HiFi-GAN (VCTK, VITS study) VITS study (public implementations)19±6comparison only2021-06

see all text-to-speech models · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 65% of its score
testresultvs the others in its rundifficultycountswhy
VITS 2021 LJ Speech human MOS3.77 / 5 ✎█····█·█·█·█ beats 0/4easy · avg 4.22 / 5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 65%at its level

$ where to run it

No verified API or download recorded yet · add one

Weights and documentation: github.com/NVIDIA ↗

$ how the score was worked out · VITS: ICML 2021 original list… 65%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
VITS: ICML 2021 original listening studies1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 65%CC-BY-4.0
prior · pull toward the middle▇▇▇▇▇▇▇▇▇▇ 35%
weighted average= 23.4

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json