Byte-based multilingual transformer TTS for low-resource/few-shot language adaptation.

Overview

One model to speak them all 🌎

Audio Language Text
Chinese 人人生而自由,在尊严和权利上一律平等。
English All human beings are born free and equal in dignity and rights.
Japanese すべての人間は、生まれながらにして自由であり、かつ、尊厳と権利とについてびょうどうである。
Korean 모든 인간은 태어날 때부터 자유로우며 그 존엄과 권리에 있어 동등하다.
German Alle Menschen sind frei und gleich an Würde und Rechten geboren.
Russian Все люди рождаются свободными и равными в своем достоинстве и правах.
Spanish Todos los seres humanos nacen libres e iguales en dignidad y derechos.
Gujarati પ્રતિષ્ઠા અને અધિકારોની દૃષ્ટિએ સર્વ માનવો જન્મથી સ્વતંત્ર અને સમાન હોય છે.
...even when there are only 30 utterances for training
Norwegian Alle mennesker er født frie og med samme menneskeverd og menneskerettigheter.
Romanian Toate ființele umane se nasc libere și egale în demnitate și în drepturi.
Greek Όλοι οι άνθρωποι γεννιούνται ελεύθεροι και ίσοι στην αξιοπρέπεια και τα δικαιώματα.

This is an implementation of the paper Multilingual Byte2Speech Models for Scalable Low-resource Speech Synthesis, which can handle 40+ languages in a single model, and learn a brand new language in few shots or minutes of recordings. The code is partially based on the open-source Tacotron2 and Transformer-TTS. More audio samples of the paper are available here.

Quickstart

We follow the paper's training recipe, but with open datasets instead. By a combination of 15 speech datasets with 572 speakers in 38 languages, we can reach results similar to what we demonstrated in the paper to an extent, as shown by the audio samples above. These datasets are listed below, the preprocessor scripts below are located at corpora/. Locations and details to download the data are also given in the respective preprocessor.

Name Preprocessor script name Languages
M-AILABS caito es-es, fr-fr, de-de, uk-ua, ru-ru, pl-pl, it-it, en-us, en-uk
CSS-10 css10 es-es, fr-fr, ja-jp, de-de, fi-fi, hu-hu, ja-jp, nl-nl, ru-ru, zh-cn
SIWIS siwis fr-fr
JSUT jsut ja-jp
KSS kss ko-kr
Databaker databaker zh-cn
LJSpeech ljspeech en-us
NST nst da-dk, nb-no
TTS-Portuguese portuguese pt-br
Thorsten Mueller thorsten de-de
Google google bn-bd, bn-in, ca-es, eu-es, gl-es, gu-in, jv-id, km-kh, kn-in, ml-in, mr-in, my-mm, ne-np, si-lk, su-id, ta-in, te-in, yo-ng
RuLS lsru ru-ru
English Bible enbible en-us
Hifi-TTS hifitts en-us, en-uk
RSS rss ro-ro

Preprocessing

  1. Please download and extract these datasets to the dataset_path specified in corpora/__init__.py. You can change the dataset_path, transformed_path and packed_path to your own.
  2. Run the preprocessor for each dataset given in corpora. The results are saved to transformed_path. include_corpus in corpora/__init__.py could be modified to add or remove datasets to be used. Particularly, you may refer to the preprocessors to include your own datasets to the training,
    and then add the dataset to include_corpus and dataset_language in corpora/__init__.py.
  3. Run the corpora/process_corpus.py, which filters the dataset, trims the audios, produces the metadata, generates the mel spectrograms, and pack all the features into a single zip file. The processed dataset will be put at packed_path, which uses around 100GB space. See the script for details.

Training

Similarly, we split the dataset into three tiers. Below are the commands to train and evaluate on each tier. Please substitute the directories with your own. The evaluation script can be run simultaneously with the training script. You may also use the evaluation script to synthesize samples from pretrained models. Please refer to the help of the arguments for their meanings.

Besides, to report CER, you need to create azure_key.json with your own Azure STT subscription, with content of {"subscription": "YOUR_KEY", "region": "YOUR_REGION"}, see utils/transcribe.py. Due to significant differences of the datasets used, the implementation is for demonstration only and could not fully reproduce the results in the paper.

T1

python -m torch.distributed.launch --nproc_per_node=NGPU train.py --model-dir=MODEL_DIR --log-dir=LOG_DIR --data-dir=DATA_DIR --training_languages=en-us:de-de:ja-jp:es-es --warmup_languages=en-us --ddp=True --eval_steps=40000:100000

python eval.py --model-dir=MODEL_DIR --log-dir=LOG_DIR --data-dir=DATA_DIR --start_step=100000 --eval_languages=en-us:de-de:ja-jp

T2

python -m torch.distributed.launch --nproc_per_node=NGPU train.py --model-dir=MODEL_DIR --log-dir=LOG_DIR --data-dir=DATA_DIR --training_languages=en-us:de-de:fr-fr:ru-ru:en-uk:es-es:uk-ua:pl-pl:it-it:ja-jp:zh-cn --ddp=True --hparams="warmup_steps=350000" --restore_from=T1_MODEL_DIR/model.ckpt-350000 --eval_steps=400000:450000 --eval_languages=zh-cn:ru-ru:it-it

python eval.py --model-dir=MODEL_DIR --log-dir=LOG_DIR --data-dir=DATA_DIR --start_step=400000 --eval_languages=zh-cn:ru-ru:it-it

T3

python -m torch.distributed.launch --nproc_per_node=NGPU train.py --model-dir=MODEL_DIR --log-dir=LOG_DIR --data-dir=DATA_DIR --training_languages=en-us:de-de:fr-fr:ru-ru:en-uk:es-es:uk-ua:pl-pl:it-it:ja-jp:zh-cn:nl-nl:fi-fi: ko-kr:eu-es:pt-br:hu-hu:jv-id:gl-es:gu-in:kn-in:da-dk:su-id:ta-in:ca-es:ml-in:te-in:my-mm:yo-ng:km-kh:mr-in:ne-np:bn-bd: bn-in:si-lk --ddp=True --hparams="warmup_steps=650000,batch_frame_quad_limit=6500000" --restore_from=T2_MODEL_DIR/model.ckpt-650000 --eval_steps=700000:750000 --eval_languages=ko-kr:da-dk:te-in

python eval.py --model-dir=MODEL_DIR --log-dir=LOG_DIR --data-dir=DATA_DIR --start_step=700000 --eval_languages=ko-kr:da-dk:te-in

Few-shot adaptation

Norwegian Bokmal (nb-no), Greek (el-gr), and Romanian (ro-ro) are excluded from the training dataset and can be used for few-shot/low-resource adaptation. The command below gives an example for adaptation to el-gr with 100 samples, and you may substitute the --adapt_languages and --downsample_languages with your own.

python -m torch.distributed.launch --nproc_per_node=NGPU train.py --model-dir=MODEL_DIR --log-dir=LOG_DIR --data-dir=DATA_DIR --training_languages=en-us:de-de:fr-fr:ru-ru:en-uk:es-es:uk-ua:pl-pl:it-it:ja-jp:zh-cn:nl-nl:fi-fi: ko-kr:eu-es:pt-br:hu-hu:jv-id:gl-es:gu-in:kn-in:da-dk:su-id:ta-in:ca-es:ml-in:te-in:my-mm:yo-ng:km-kh:mr-in:ne-np: bn-bd:bn-in:si-lk --adapt_languages=el-gr --downsample_languages=el-gr:100 --ddp=True --hparams="warmup_steps=800000" --restore_from=T3_MODEL_DIR/model.ckpt-700000

python eval.py --model-dir=MODEL_DIR --log-dir=LOG_DIR --data-dir=DATA_DIR --start_step=700000 --eval_languages=el-gr

Performance

Below listed the best CERs of selected languages reached by models from each tier on these open datasets, as well as the CERs on few-shot adaptation. The CERs are based on Azure Speech-to-Text.

T1 en-us de-de ja-jp
2.68% 2.17% 19.06%
T2 it-it ru-ru zh-cn
1.95% 3.21% 7.30%
T3 da-dk ko-kr te-in
1.31% 0.94% 4.41%

Adaptation

#Samples nb-no el-gr ro-ro
30 9.18% 5.71% 5.58%
100 3.63% 4.63% 4.89%

Pretrained Models

The pretrained models are available at OneDrive Link. Metadata for eval are also given to aid fast reproduction. Below listed are the models provided.

Base models

  • T1 350k steps, ready for T2
  • T2 650k steps, ready for T3
  • T3 700k steps, ready for adaptation
  • T3 1.16M steps, which reaches satisfactory performances on most languages

Few-shot adaptation

  • nb-no, 30 samples, at 710k steps
  • nb-no, 100 samples, at 750k steps
  • el-gr, 30 samples, at 1M steps
  • el-gr, 100 samples, at 820k steps
  • ro-ro, 30 samples, at 970k steps
  • ro-ro, 100 samples, at 910k steps

Synthesis

To synthesize audios from the pretrained models, download the models along with the metadata files (lang_id.json and spk_id.json). Since there are no ground truth mels, you need to create metadata with dummy mel targets information , and run eval.py without neither --zipfilepath specified nor mels.zip present in --data-dir. The metadata file takes the form of SPEAKERNAME_FILEID|DUMMY_LENGTH|TEXT|LANG for each line of the file. For example, you can generate the audio examples above by saving the following metadata to script.txt:

databaker_0|500|人人生而自由,在尊严和权利上一律平等。|zh-cn
ljspeech_0|500|All human beings are born free and equal in dignity and rights.|en-us
jsut_0|500|すべての人間は、生まれながらにして自由であり、かつ、尊厳と権利とについてびょうどうである。|ja-jp
kss_0|500|모든 인간은 태어날 때부터 자유로우며 그 존엄과 권리에 있어 동등하다.|ko-kr
thorsten_0|500|Alle Menschen sind frei und gleich an Würde und Rechten geboren.|de-de
hajdurova_0|500|Все люди рождаются свободными и равными в своем достоинстве и правах.|ru-ru
tux_0|500|Todos los seres humanos nacen libres e iguales en dignidad y derechos.|es-es
guf02858_0|500|પ્રતિષ્ઠા અને અધિકારોની દૃષ્ટિએ સર્વ માનવો જન્મથી સ્વતંત્ર અને સમાન હોય છે.|gu-in

, and with the command python eval.py --model-dir=T3_MODEL_DIR --log-dir=OUTPUT_DIR --data-dir=METADATA_DIR --eval_meta=script.txt --eval_step=1160000 --no_wait=True. You may refer to lang_id.json and spk_id.json to synthesize audios with other languages or speakers.

The waveforms are produced by Griffin-Lim, while mel spectrograms are also saved to SPEAKERNAME_FILEID.npy, which are normalized to a [-4, 4] range. Pretrained vocoders like Wavenet can be used to reach better quality. Those using recipes similar to Tacotron2 should be applicable to these mels, although you need to map mels to a range of [0, 1], simply by mels = (mels + 8) / 4.

Owner
Mutian He
Mutian He
AI Face Mesh: This is a simple face mesh detection program based on Artificial intelligence.

AI Face Mesh: This is a simple face mesh detection program based on Artificial Intelligence which made with Python. It's able to detect 468 different

Md. Rakibul Islam 1 Jan 13, 2022
Code for a seq2seq architecture with Bahdanau attention designed to map stereotactic EEG data from human brains to spectrograms, using the PyTorch Lightning.

stereoEEG2speech We provide code for a seq2seq architecture with Bahdanau attention designed to map stereotactic EEG data from human brains to spectro

15 Nov 11, 2022
Solving reinforcement learning tasks which require language and vision

Multimodal Reinforcement Learning JAX implementations of the following multimodal reinforcement learning approaches. Dual-coding Episodic Memory from

Henry Prior 31 Feb 26, 2022
Anonymous implementation of KSL

k-Step Latent (KSL) Implementation of k-Step Latent (KSL) in PyTorch. Representation Learning for Data-Efficient Reinforcement Learning [Paper] Code i

1 Nov 10, 2021
Algorithmic Trading using RNN

Deep-Trading This an implementation adapted from Rachnog Neural networks for algorithmic trading. Part One — Simple time series forecasting and this c

Hazem Nomer 29 Sep 04, 2022
Learning Skeletal Articulations with Neural Blend Shapes

This repository provides an end-to-end library for automatic character rigging and blend shapes generation as well as a visualization tool. It is based on our work Learning Skeletal Articulations wit

Peizhuo 504 Dec 30, 2022
A python bot to move your mouse every few seconds to appear active on Skype, Teams or Zoom as you go AFK. 🐭 🤖

PyMouseBot If you're from GT and annoyed with SGVPN idle timeouts while working on development laptop, You might find this useful. A python cli bot to

Oaker Min 6 Oct 24, 2022
[CVPR21] LightTrack: Finding Lightweight Neural Network for Object Tracking via One-Shot Architecture Search

LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search The official implementation of the paper LightTra

Multimedia Research 290 Dec 24, 2022
This is a Python wrapper for TA-LIB based on Cython instead of SWIG.

TA-Lib This is a Python wrapper for TA-LIB based on Cython instead of SWIG. From the homepage: TA-Lib is widely used by trading software developers re

John Benediktsson 7.3k Jan 03, 2023
TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification

TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification [NeurIPS 2021] Abstract Multiple instance learn

132 Dec 30, 2022
Fluency ENhanced Sentence-bert Evaluation (FENSE), metric for audio caption evaluation. And Benchmark dataset AudioCaps-Eval, Clotho-Eval.

FENSE The metric, Fluency ENhanced Sentence-bert Evaluation (FENSE), for audio caption evaluation, proposed in the paper "Can Audio Captions Be Evalua

Zhiling Zhang 13 Dec 23, 2022
The official PyTorch implementation of paper BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition

BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition Boyan Zhou, Quan Cui, Xiu-Shen Wei*, Zhao-Min Chen This repo

Megvii-Nanjing 616 Dec 21, 2022
Unified file system operation experience for different backend

megfile - Megvii FILE library Docs: http://megvii-research.github.io/megfile megfile provides a silky operation experience with different backends (cu

MEGVII Research 76 Dec 14, 2022
This project hosts the code for implementing the ISAL algorithm for object detection and image classification

Influence Selection for Active Learning (ISAL) This project hosts the code for implementing the ISAL algorithm for object detection and image classifi

25 Sep 11, 2022
Code for visualizing the loss landscape of neural nets

Visualizing the Loss Landscape of Neural Nets This repository contains the PyTorch code for the paper Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer

Tom Goldstein 2.2k Jan 09, 2023
Multi agent DDPG algorithm written in Python + Pytorch

Multi agent DDPG algorithm written in Python + Pytorch. It also includes a Jupyter notebook, Tennis.ipynb, as a showcase.

Rogier Wachters 2 Feb 26, 2022
African language Speech Recognition - Speech-to-Text

Swahili-Speech-To-Text Table of Contents Swahili-Speech-To-Text Overview Scenario Approach Project Structure data: models: notebooks: scripts tests: l

2 Jan 05, 2023
MAME is a multi-purpose emulation framework.

MAME's purpose is to preserve decades of software history. As electronic technology continues to rush forward, MAME prevents this important "vintage" software from being lost and forgotten.

Michael Murray 6 Oct 25, 2020
Implementation of Perceiver, General Perception with Iterative Attention in TensorFlow

Perceiver This Python package implements Perceiver: General Perception with Iterative Attention by Andrew Jaegle in TensorFlow. This model builds on t

Rishit Dagli 84 Oct 15, 2022
This is the official Pytorch implementation of "Lung Segmentation from Chest X-rays using Variational Data Imputation", Raghavendra Selvan et al. 2020

README This is the official Pytorch implementation of "Lung Segmentation from Chest X-rays using Variational Data Imputation", Raghavendra Selvan et a

Raghav 42 Dec 15, 2022