whatmodel.sh / tts / FastPitch 1.1 + WaveGlow

FastPitch 1.1 + WaveGlow

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

FastPitch 1.1 + WaveGlow is an open-weights text-to-speech model from NVIDIA, released August 2021. Licence: bsd-3-clause.

Catalogue identity notes

Exact NVIDIA implementation with WaveGlow vocoder. Do not transfer these listening-study values to Coqui, SpeechBrain, HiFi-GAN or a differently trained checkpoint. Historical run dependencies documented upstream; no current one-command run verified.

Model information sources

· Weights licence ↗

No comparable score yet. Its published results are below, but they don't overlap enough with other models to calculate a score.

$ how it compares

Scored text-to-speech models released closest to FastPitch 1.1 + WaveGlow, out of 148 with a score, then more from NVIDIA.

#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
more from NVIDIA
113Magpie TTS Multilingual 357M NVIDIA39±6local~0.7GB2026-07

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

$ what it's good at

other tests1 not in a task · 0.0% of its score
testresultvs the others in its rundifficultycountswhy
FastPitch 1.0 vs 1.1 pairwise preference (2021) lab56.5% ✎█··········█ beats 1/1—not counted yet: no other model in the same run to compare it with

$ where to run it

Other ways to run it

  1. Run it as published · needs ~1.24 GB, NVIDIA only · from github.com/NVIDIA (official)
    git clone https://github.com/NVIDIA/DeepLearningExamples.git && cd DeepLearningExamples/PyTorch/SpeechSynthesis/FastPitch && bash scripts/docker/build.sh && docker run --gpus=all --rm --ipc=host -v $PWD:/workspace/fastpitch/ fastpitch:latest bash -c "bash scripts/download_cmudict.sh && HIFIGAN= WAVEGLOW=pretrained_models/waveglow/nvidia_waveglow256pyt_fp16.pt bash scripts/inference_example.sh"

Official weights and documentation: github.com/NVIDIA ↗

$ published results · 1 result, not enough overlap for a score
testresultsource and conditions
FastPitch 1.0 vs 1.1 pairwise preference (2021)56.5%NVIDIA FastPitch: original listening studies in committed README · lab-reported

Committed README Average preference table, ±0.068. Pairwise preference between versions 1.0 and 1.1, not human MOS. Stored unchanged.

$ 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