whatmodel.sh / tts / PriorGrad acoustic + HiFi-GAN

PriorGrad acoustic + HiFi-GAN

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

PriorGrad acoustic + HiFi-GAN is an open-weights text-to-speech model from Microsoft NeuralSpeech, released June 2021.

Catalogue identity notes

Original author implementation with linked pretrained acoustic and vocoder weights. Legacy environment requires a multi-step setup. No benchmark score or current one-command run inferred.

No comparable score yet. No reviewed benchmark results yet.

$ how it compares

Scored text-to-speech models released closest to PriorGrad acoustic + HiFi-GAN, 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

$ where to run it

Other ways to run it

  1. Run it as published · needs ~0.28 GB, NVIDIA only · from github.com/microsoft (official)
    git clone https://github.com/microsoft/NeuralSpeech.git && cd NeuralSpeech/PriorGrad-acoustic && SKLEARN_ALLOW_DEPRECATED_SKLEARN_PACKAGE_INSTALL=True pip install -r requirements.txt && git submodule init && git submodule update && wget https://huggingface.co/neuralspeech/priorgrad/resolve/main/ljspeech_hfg.zip && unzip ljspeech_hfg.zip -d data && wget https://huggingface.co/neuralspeech/priorgrad/resolve/main/priorgrad_am.zip && unzip priorgrad_am.zip -d checkpoints && mkdir hifigan_pretrained && curl -L -o hifigan_pretrained/generator_v1 'https://drive.usercontent.google.com/download?id=14NENd4equCBLyyCSke114Mv6YR_j_uFs&export=download&confirm=t' && curl -L -o hifigan_pretrained/config.json 'https://drive.usercontent.google.com/download?id=1aDh576AEYA5eTjhx7sew1qcCM_Y526jc&export=download&confirm=t' && CUDA_VISIBLE_DEVICES=0 PYTHONPATH=. python tasks/priorgrad_inference.py --config configs/tts/lj/priorgrad.yaml --exp_name priorgrad --reset --inference_text inference_text.txt --fast --fast_iter 12

Official weights and documentation: github.com/microsoft ↗

$ 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