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

Zhengxi Liu (刘正曦)

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)

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

Related tags

Overview

Fast (GAN Based Neural) Vocoder

Todo

Discription

Usage

Acknowledgments

Comments

why set the L=30 ?

Link to Basis-MelGAN paper?

Random start index in WeightDataset

can basis-melgan be used as unversial vocoder?

Shape mismatch error on new dataset

Multiband Architecture

Releases(v1.0)

v1.0(Jun 24, 2021)

Owner

Zhengxi Liu (刘正曦)

STS Benchmark comprises a selection of the English datasets used in the STS tasks organized in the context of SemEval between 2012 and 2017. The selection of datasets include text from image captions, news headlines and user forums.

A CRM department in a local bank works on classify their lost customers with their past datas. So they want predict with these method that average loss balance and passive duration for future.

Ptorch NLU, a Chinese text classification and sequence annotation toolkit, supports multi class and multi label classification tasks of Chinese long text and short text, and supports sequence annotation tasks such as Chinese named entity recognition, part of speech tagging and word segmentation.

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

VADER Sentiment Analysis. VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social media, and works well on texts from other domains.

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

VADER Sentiment Analysis. VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social media, and works well on texts from other domains.

Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation, available for both PyTorch and Tensorflow.

:id: A python library for accurate and scalable fuzzy matching, record deduplication and entity-resolution.

Jarvis is a simple Chatbot with a GUI capable of chatting and retrieving information and daily news from the internet for it's user.

Client library to download and publish models and other files on the huggingface.co hub

Data loaders and abstractions for text and NLP

:id: A python library for accurate and scalable fuzzy matching, record deduplication and entity-resolution.

Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

Data loaders and abstractions for text and NLP