Include MelGAN, HifiGAN and Multiband-HifiGAN, maybe NHV in the future.

Last update: Dec 16, 2022

Related tags

Text Data & NLP FastVocoder

Overview

Fast (GAN Based Neural) Vocoder

Chinese README

Todo

Submit demo
Support NHV

Discription

Include MelGAN, HifiGAN and Multiband-HifiGAN, maybe include NHV in the future. Developed on BiaoBei dataset, you can modify conf and hparams.py to fit your own dataset and model.

Usage

Prepare data
- write path of wav data in a file, for example: cd dataset && python3 biaobei.py
- bash preprocess.sh <wav path file> <path to save processed data> dataset/audio dataset/mel
- for example: bash preprocess.sh dataset/BZNSYP.txt processed dataset/audio dataset/mel

Train

command:

bash train.sh \
    <GPU ids> \
    /path/to/audio/train \
    /path/to/audio/valid \
    /path/to/mel/train \
    /path/to/mel/valid \
    <model name> \
    <if multi band> \
    <if use scheduler> \
    <path to configuration file>

for example:

bash train.sh \
0 \
dataset/audio/train \
dataset/audio/valid \
dataset/mel/train \
dataset/mel/valid \
hifigan \
0 0 0 \
conf/hifigan/light.yaml

Train from checkpoint

command:

bash train.sh \
    <GPU ids> \
    /path/to/audio/train \
    /path/to/audio/valid \
    /path/to/mel/train \
    /path/to/mel/valid \
    <model name> \
    <if multi band> \
    <if use scheduler> \
    <path to configuration file> \
    /path/to/checkpoint \
    <step of checkpoint>

Synthesize

command:

bash synthesize.sh \
    /path/to/checkpoint \
    /path/to/mel \
    /path/for/saving/wav \
    <model name> \
    /path/to/configuration/file

Acknowledgments

Comments

why set the L=30 ?

hello，I have some question， in the paper ，the shape of basis matrix is [32, 256] , but in the code ,the shape is [30, 256] . And according to the function "overlap_and_add" , output_size = (frames - 1) * frame_step + frame_length, if the L=30, I think it cannot match the real wave length ? for example, hop_len=256, mel.shape=[80, 140] , theoretically the output wave length is 140*256=35840. according to the code, the output wave length is 33600.

Thanks in advance.

opened by yingfenging 3
Link to Basis-MelGAN paper?

Hi Zhengxi, congrats on your paper's acceptance on Interspeech 2021!

I got pretty interested in your paper while reading the abstract of Basis-MelGAN on the README, but I could not find any link to the paper. Though the Interspeech conference is only 2 months away, don't you have any plans on publishing the paper on arXiv in near future?

opened by seungwonpark 2
Random start index in WeightDataset

At this line: https://github.com/xcmyz/FastVocoder/blob/a9af370be896b1096e746ce6489fb16fef8ca585/data/dataset.py#L97

If the input mel size smaller than fix-length, the random raise issue, I have try except to pass these short audios, but I just wonder it is handle in collate.

More than that, the segment size as I found in hifigan is 32, but in basic-melgan it (fix-length) is set to 140. Are there any difference between the 140 for biaobei and the one for LJspeech

opened by v-nhandt21 0
can basis-melgan be used as unversial vocoder?

I tried it for a single speaker dataset, rtf surprises me. Have you ever use basis-melgan for a multi-speaker dataset, or is it suitable for unseen speaker tts synthesis?

opened by mayfool 0
Shape mismatch error on new dataset
Hi, thanks for your work!

The frame rate of my dataset is 22050, and hop size of text2mel model is 256. I have changed hparams.py accordingly, but training results in an expcetion: (preprocessing was fine, anyway)

File "/home/user/speechlab/FastVocoder-main/model/loss/loss.py", line 23, in forward assert est_source_sub_band.size(1) == wav_sub_band.size(1)

I figured out that model inference still uses hop-size of 240. So how to make your code fully compatible with other datasets? it seems that the codes are somehow hardcoded for Biaobei dataset.
opened by tekinek 1
Multiband Architecture

Hi author, I have found the notes as "the generated audio has interference at a specific frequency" in this repo. I have encountered with the straight line at a specific frequency when developing similar multiband architecture, and I wonder if such phenomenon is the one you mentioned? And do you have some advice or solutions? Thanks.
help wanted

opened by Rongjiehuang 6

Releases(v1.0)

v1.0(Jun 24, 2021)

Source code(tar.gz)
Source code(zip)
basis.melgan.pt(53.36 MB)

Owner

Zhengxi Liu (刘正曦)

Interested in high performance neural vocoder and expressive TTS acoustic model. Member of DeepMist and developed MistGPU.

GitHub Repository

A very simple framework for state-of-the-art Natural Language Processing (NLP)

A very simple framework for state-of-the-art NLP. Developed by Humboldt University of Berlin and friends. IMPORTANT: (30.08.2020) We moved our models

12.3k Dec 31, 2022

KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)

KoGPT KoGPT (Korean Generative Pre-trained Transformer) https://github.com/kakaobrain/kogpt https://huggingface.co/kakaobrain/kogpt Model Descriptions

797 Dec 26, 2022

Python bindings to the dutch NLP tool Frog (pos tagger, lemmatiser, NER tagger, morphological analysis, shallow parser, dependency parser)

Frog for Python This is a Python binding to the Natural Language Processing suite Frog. Frog is intended for Dutch and performs part-of-speech tagging

46 Dec 14, 2022

Bidirectional Variational Inference for Non-Autoregressive Text-to-Speech (BVAE-TTS)

Bidirectional Variational Inference for Non-Autoregressive Text-to-Speech (BVAE-TTS) Yoonhyung Lee, Joongbo Shin, Kyomin Jung Abstract: Although early

147 Dec 05, 2022

端到端的长本文摘要模型（法研杯2020司法摘要赛道）

端到端的长文本摘要模型（法研杯2020司法摘要赛道）

334 Jan 08, 2023

Conditional probing: measuring usable information beyond a baseline

20 Dec 15, 2022

Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers

beyond masking Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers The code is coming Figure 1: Pipeline of token-based pre-

23 Sep 27, 2022

Binaural Speech Synthesis

Binaural Speech Synthesis This repository contains code to train a mono-to-binaural neural sound renderer. If you use this code or the provided datase

135 Dec 18, 2022

AI and Machine Learning workflows on Anthos Bare Metal.

Hybrid and Sovereign AI on Anthos Bare Metal Table of Contents Overview Terraform as IaC Substrate ABM Cluster on GCE using Terraform TensorFlow ResNe

8 Nov 26, 2022

Words-per-minute - A terminal app written in python utilizing the curses module that tests the user's ability to type

words-per-minute A terminal app written in python utilizing the curses module th

1 Jan 14, 2022

Beyond the Imitation Game collaborative benchmark for enormous language models

BIG-bench 🪑 The Beyond the Imitation Game Benchmark (BIG-bench) will be a collaborative benchmark intended to probe large language models, and extrap

1.3k Jan 01, 2023

Official Stanford NLP Python Library for Many Human Languages

6.4k Jan 02, 2023

Converts text into a PDF of handwritten notes

Text To Handwritten Notes Converts text into a PDF of handwritten notes Explore the docs » · Report Bug · Request Feature · Steps: $ git clone https:/

63 Oct 09, 2022

Use AutoModelForSeq2SeqLM in Huggingface Transformers to train COMET

Training COMET using seq2seq setting Use AutoModelForSeq2SeqLM in Huggingface Transformers to train COMET. The codes are modified from run_summarizati