HiFi-GAN
An 16kHz implementation of HiFi-GAN for soft-vc.
Relevant links:
Example Usage
import torch
import numpy as np
# Load checkpoint
hifigan = torch.hub.load("bshall/hifigan:main", "hifigan_hubert_soft").cuda()
# Load mel-spectrogram
mel = torch.from_numpy(np.load("path/to/mel")).unsqueeze(0).cuda()
# Generate
wav, sr = hifigan.generate(mel)
Train
Step 1: Download and extract the LJ-Speech dataset
Step 2: Resample the audio to 16kHz:
usage: resample.py [-h] [--sample-rate SAMPLE_RATE] in-dir out-dir
Resample an audio dataset.
positional arguments:
in-dir path to the dataset directory
out-dir path to the output directory
optional arguments:
-h, --help show this help message and exit
--sample-rate SAMPLE_RATE
target sample rate (default 16kHz)
Step 3: Download the dataset splits and move them into the root of the dataset directory. After steps 2 and 3 your dataset directory should look like this:
LJSpeech-1.1
│ test.txt
│ train.txt
│ validation.txt
├───mels
└───wavs
Note: the mels directory is optional. If you want to fine-tune HiFi-GAN the mels directory should contain ground-truth aligned spectrograms from an acoustic model.
Step 4: Train HiFi-GAN:
usage: train.py [-h] [--resume RESUME] [--finetune] dataset-dir checkpoint-dir
Train or finetune HiFi-GAN.
positional arguments:
dataset-dir path to the preprocessed data directory
checkpoint-dir path to the checkpoint directory
optional arguments:
-h, --help show this help message and exit
--resume RESUME path to the checkpoint to resume from
--finetune whether to finetune (note that a resume path must be given)
Generate
To generate using the trained HiFi-GAN models, see Example Usage or use the generate.py script:
usage: generate.py [-h] [--model-name {hifigan,hifigan-hubert-soft,hifigan-hubert-discrete}] in-dir out-dir
Generate audio for a directory of mel-spectrogams using HiFi-GAN.
positional arguments:
in-dir path to directory containing the mel-spectrograms
out-dir path to output directory
optional arguments:
-h, --help show this help message and exit
--model-name {hifigan,hifigan-hubert-soft,hifigan-hubert-discrete}
available models
Acknowledgements
This repo is based heavily on https://github.com/jik876/hifi-gan.
3 Oct 29, 2022
7 Jul 10, 2022
8 Sep 30, 2022
![[ICLR 2022] Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics](https://github.com/lester0866/CPDeform/raw/main/demo/writer_demo.gif)
29 Nov 29, 2022
1.5k Jan 2, 2023
72 Dec 31, 2022
43 Dec 27, 2022
46 Sep 5, 2022
23 Dec 21, 2022
6 Sep 07, 2022
139 Jan 01, 2023
69 Dec 29, 2022
6 Jun 05, 2022
5 Jan 25, 2022
351 Nov 18, 2022
12 Jun 27, 2022
607 Dec 31, 2022
[email protected])">
581 Dec 30, 2022
1 Mar 29, 2022
1 Jan 09, 2022
2k Dec 31, 2022
134 Nov 20, 2022
4 Dec 31, 2022
0 Nov 19, 2021
16 Oct 29, 2022
46 Nov 17, 2022
74 Nov 22, 2022
9 Nov 22, 2022