Easy-to-use Speech Toolkit including SOTA/Streaming ASR with punctuation, influential TTS with text frontend, Speaker Verification System and End-to-End Speech Simultaneous Translation.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 
Go to file
Mingxue-Xu 718c7b3187
Add ASR samples.
3 years ago
.github add stale config (#604) 4 years ago
.pre-commit-hooks add pre commit hooks 4 years ago
.travis E2E/Streaming Transformer/Conformer ASR (#578) 4 years ago
deepspeech trainer eval when not train 3 years ago
docs Add ASR samples. 3 years ago
examples Merge pull request #908 from PaddlePaddle/speech 3 years ago
hub add requirements for hub 3 years ago
parakeet merge parakeet repo into deepspeech 3 years ago
speechnn fix for kaldi 3 years ago
tests merge parakeet repo into deepspeech 3 years ago
third_party Kaldi (#839) 3 years ago
tools u2 kaldi mutli process test with batchsize one 3 years ago
utils Merge pull request #908 from PaddlePaddle/speech 3 years ago
.bashrc fix bugs 3 years ago
.clang-format E2E/Streaming Transformer/Conformer ASR (#578) 4 years ago
.flake8 refactor feature, dict and argument for new config format 3 years ago
.gitconfig E2E/Streaming Transformer/Conformer ASR (#578) 4 years ago
.gitignore fix sctk install 3 years ago
.mergify.yml add delpoy mergify label 4 years ago
.pre-commit-config.yaml E2E/Streaming Transformer/Conformer ASR (#578) 4 years ago
.readthedocs.yml merge parakeet repo into deepspeech 3 years ago
.style.yapf Add ci and code format checking. 7 years ago
.travis.yml E2E/Streaming Transformer/Conformer ASR (#578) 4 years ago
.vimrc E2E/Streaming Transformer/Conformer ASR (#578) 4 years ago
LICENSE Create License 7 years ago
README.md Add ASR samples. 3 years ago
env.sh fix env.sh PATH postion 3 years ago
requirements.txt close editdistance package format warning 3 years ago
setup.py merge parakeet repo into deepspeech 3 years ago
setup.sh refactor raw ctc decoder into ctcdecoder 3 years ago

README.md

English | 简体中文


License python version support os

PaddleSpeech is an open-source toolkit on PaddlePaddle platform for a variety of critical tasks in speech, with the state-of-art and influential models.

Speech-To-Text
Input Audio Recognition Result

I knocked at the door on the ancient side of the building.

我认为跑步最重要的就是给我带来了身体健康。
Text-To-Speech
Input Text Synthetic Audio
Life was like a box of chocolates, you never know what you're gonna get.
早上好今天是2020/10/29最低温度是-3°C。

Via the easy-to-use, efficient, flexible and scalable implementation, our vision is to empower both industrial application and academic research, including training, inference & testing modules, and deployment process. To be more specific, this toolkit features at:

  • Fast and Light-weight: we provide high-speed and ultra-lightweight models that are convenient for industrial deployment.
  • Rule-based Chinese frontend: our frontend contains Text Normalization and Grapheme-to-Phoneme (G2P, including Polyphone and Tone Sandhi). Moreover, we use self-defined linguistic rules to adapt Chinese context.
  • Varieties of Functions that Vitalize both Industrial and Academia:
    • Implementation of critical audio tasks: this toolkit contains audio functions like Speech Translation, Automatic Speech Recognition, Text-To-Speech Synthesis, Voice Cloning, etc.
    • Integration of mainstream models and datasets: the toolkit implements modules that participate in the whole pipeline of the speech tasks, and uses mainstream datasets like LibriSpeech, LJSpeech, AIShell, CSMSC, etc. See also model lists for more details.
    • Cascaded models application: as an extension of the application of traditional audio tasks, we combine the workflows of aforementioned tasks with other fields like Natural language processing (NLP), like Punctuation Restoration.

Community

You are warmly welcome to submit questions in discussions and bug reports in issues! Also, we highly appreciate if you would like to contribute to this project!

If you are from China, we strongly recommend you join our PaddleSpeech WeChat group. Scan the following WeChat QR code and get in touch with the other developers in this community!

Alternative Installation

The base environment in this page is

  • Ubuntu 16.04
  • python>=3.7
  • paddlepaddle==2.1.2

If you want to set up PaddleSpeech in other environment, please see the installation documents for all the alternatives.

Quick Start

Developers can have a try of our model with only a few lines of code.

A tiny DeepSpeech2 Speech-To-Text model training on toy set of LibriSpeech:

cd examples/tiny/s0/
# source the environment
source path.sh
# prepare librispeech dataset
bash local/data.sh
# evaluate your ckptfile model file
bash local/test.sh conf/deepspeech2.yaml ckptfile offline

For Text-To-Speech, try FastSpeech2 on LJSpeech:

  • Download LJSpeech-1.1 from the ljspeech official website, our prepared durations for fastspeech2 ljspeech_alignment.
  • The pretrained models are seperated into two parts: fastspeech2_nosil_ljspeech_ckpt and pwg_ljspeech_ckpt. Please download then unzip to ./model/fastspeech2 and ./model/pwg respectively.
  • Assume your path to the dataset is ~/datasets/LJSpeech-1.1 and ./ljspeech_alignment accordingly, preprocess your data and then use our pretrained model to synthesize:
cd examples/csmsc/tts3
# download the pretrained models and unaip them
wget https://paddlespeech.bj.bcebos.com/Parakeet/pwg_baker_ckpt_0.4.zip
unzip pwg_baker_ckpt_0.4.zip
wget https://paddlespeech.bj.bcebos.com/Parakeet/fastspeech2_nosil_baker_ckpt_0.4.zip
unzip fastspeech2_nosil_baker_ckpt_0.4.zip
# source the environment
source path.sh
# run end-to-end synthesize
FLAGS_allocator_strategy=naive_best_fit \
FLAGS_fraction_of_gpu_memory_to_use=0.01 \
python3 ${BIN_DIR}/synthesize_e2e.py \
  --fastspeech2-config=fastspeech2_nosil_baker_ckpt_0.4/default.yaml \
  --fastspeech2-checkpoint=fastspeech2_nosil_baker_ckpt_0.4/snapshot_iter_76000.pdz \
  --fastspeech2-stat=fastspeech2_nosil_baker_ckpt_0.4/speech_stats.npy \
  --pwg-config=pwg_baker_ckpt_0.4/pwg_default.yaml \
  --pwg-checkpoint=pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz \
  --pwg-stat=pwg_baker_ckpt_0.4/pwg_stats.npy \
  --text=${BIN_DIR}/../sentences.txt \
  --output-dir=exp/default/test_e2e \
  --inference-dir=exp/default/inference \
  --device="gpu" \
  --phones-dict=fastspeech2_nosil_baker_ckpt_0.4/phone_id_map.txt

If you want to try more functions like training and tuning, please see Speech-To-Text getting started and Text-To-Speech Basic Use.

Models List

PaddleSpeech supports a series of most popular models, summarized in released models Speech-To-Text/Text-To-Speech with available pretrained models.

Speech-To-Text module contains Acoustic Model and Language Model, with the following details:

Speech-To-Text Module Type Dataset Model Type Link
Acoustic Model Aishell DeepSpeech2 RNN + Conv based Models Online / Offline
Transformer based Attention Models Non-CTC Loss / CTC Loss
Librispeech Transformer based Attention Models Conformer / Transformer Decoder
Language Model CommonCrawl(en.00) English Language Model English Language Model
Baidu Internal Corpus Mandarin Language Model Small Mandarin Language Model Small / Large

PaddleSpeech Text-To-Speech mainly contains three modules: Text Frontend, Acoustic Model and Vocoder. Acoustic Model and Vocoder models are listed as follow:

Text-To-Speech Module Type Model Type Dataset Link
Text Frontend chinese-fronted
Acoustic Model Tacotron2 LJSpeech tacotron2-ljspeech
TransformerTTS transformer-ljspeech
SpeedySpeech CSMSC speedyspeech-csmsc
FastSpeech2 AISHELL-3 / VCTK / LJSpeech / CSMSC fastspeech2-aishell3 / fastspeech2-vctk / fastspeech2-ljspeech / fastspeech2-csmsc
Vocoder WaveFlow LJSpeech waveflow-ljspeech
Parallel WaveGAN LJSpeech / VCTK / CSMSC PWGAN-ljspeech / PWGAN-vctk / PWGAN-csmsc
Voice Cloning GE2E AISHELL-3, etc. ge2e
GE2E + Tactron2 AISHELL-3 ge2e-tactron2-aishell3

Tutorials

Normally, Speech SoTA gives you an overview of the hot academic topics in speech. To focus on the tasks in PaddleSpeech, you will find the following guidelines are helpful to grasp the core ideas.

License and Acknowledgement

PaddleSpeech is provided under the Apache-2.0 License.

PaddleSpeech depends on a lot of open source repositories. See references for more information.

Citation

To cite PaddleSpeech for research, please use the following format.

@misc{ppspeech2021,
title={PaddleSpeech, a toolkit for audio processing based on PaddlePaddle.},
author={PaddlePaddle Authors},
howpublished = {\url{https://github.com/PaddlePaddle/DeepSpeech}},
year={2021}
}