Skip to content

Scarfmonster/HiFiPLN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

2166df1 · May 4, 2024
Dec 27, 2023
May 4, 2024
Feb 4, 2024
May 4, 2024
Nov 5, 2023
Nov 11, 2023
Feb 4, 2024
Dec 14, 2023
May 4, 2024
Jan 15, 2024
Nov 20, 2023
Jan 31, 2024
Dec 27, 2023
May 4, 2024
May 4, 2024
Jan 30, 2024

Repository files navigation

HiFiPLN

Multispeaker Community Vocoder model for DiffSinger

This is the code used to train the "HiFiPLN" vocoder.

A trained model for use with OpenUtau is available for download on the official release page.

Why HiFiPLN?

Because a lot of PLN was spent training this thing.

Training

Python

Python 3.10 or greater is required.

Data preparation

python dataset-utils/split.py --length 1 -sr 44100 -o "dataset/train" PATH_TO_DATASET

You will also need to provide some validation audio files and save them to dataset/valid and then run:

python preproc.py --path dataset --config "configs/hifipln.yaml"

Train model

python train.py --config "configs/hifipln.yaml"
  • If you see an error saying "Total length of `Data Loader` across ranks is zero" then you do not have enough validation files.
  • You may want to edit configs/hifipln.yaml and change train: batch_size: 12 to a value that better fits your available VRAM.

Resume

python train.py --config "configs/hifipln.yaml" --resume CKPT_PATH

You may set CKPT_PATH to a log directory (eg. logs/HiFiPLN), and it will find the last checkpoint of the last run.

Finetuning

Download a checkpoint from https://utau.pl/hifipln/#checkpoints-for-finetuning
Save the checkpoint as ckpt/HiFiPLN.ckpt then run:

python train.py --config "configs/hifipln-finetune.yaml"
  • Finetuning shouldn't be run for too long, especially for small datasets. Just 2-3 epochs or ~20000 steps should be fine.

Exporting for use in OpenUtau

python export.py --config configs/hifipln.yaml --output out/hifipln --model CKPT_PATH

You may set CKPT_PATH to a log directory (eg. logs/HiFiPLN), and it will find the last checkpoint of the last run.

Credits