(简体中文|English)

Quick Start | Tutorials | Models List

---

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

Speech Recognition

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。

Speech Translation (English to Chinese)

Input Audio	Translations Result
	我 在 这栋 建筑 的 古老 门上 敲门。

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。

For more synthesized audios, please refer to PaddleSpeech Text-to-Speech samples.

Features:

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:

• 📦 Ease of Use: low barriers to install, and CLI is available to quick-start your journey.
• 🏆 Align to the State-of-the-Art: we provide high-speed and ultra-lightweight models, and also cutting-edge technology.
• 💯 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 Audio Classification, Speech Translation, Automatic Speech Recognition, Text-to-Speech Synthesis, 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 list for more details.
  • 🧩 Cascaded models application: as an extension of the typical traditional audio tasks, we combine the workflows of the aforementioned tasks with other fields like Natural language processing (NLP) and Computer Vision (CV).

Recent Update:

• 🤗 2021.12.14: Our PaddleSpeech ASR and TTS Demos on Hugging Face Spaces are available!
• 👏🏻 2021.12.10: PaddleSpeech CLI is available for Audio Classification, Automatic Speech Recognition, Speech Translation (English to Chinese) and Text-to-Speech.

Community

• Scan the QR code below with your Wechat, you can access to official technical exchange group. Look forward to your participation.

Installation

We strongly recommend our users to install PaddleSpeech in Linux with python>=3.7, where paddlespeech can be easily installed with pip:

pip install paddlepaddle paddlespeech

Up to now, Linux supports CLI for the all our tasks, Mac OSX and Windows only supports PaddleSpeech CLI for Audio Classification, Speech-to-Text and Text-to-Speech. Please see installation for other alternatives.

Quick Start

Developers can have a try of our models with PaddleSpeech Command Line. Change --input to test your own audio/text.

Audio Classification

paddlespeech cls --input input.wav

Automatic Speech Recognition

paddlespeech asr --lang zh --input input_16k.wav

Speech Translation (English to Chinese)

(not support for Mac and Windows now)

paddlespeech st --input input_16k.wav

Text-to-Speech

paddlespeech tts --input "你好，欢迎使用飞桨深度学习框架！" --output output.wav

• web demo for Text to Speech is integrated to Huggingface Spaces with Gradio. See Demo: TTS Demo

If you want to try more functions like training and tuning, please have a look at Speech-to-Text Quick Start and Text-to-Speech Quick Start.

Model List

PaddleSpeech supports a series of most popular models. They are summarized in released models and attached with available pretrained models.

Speech-to-Text contains Acoustic Model, Language Model, and Speech Translation, with the following details:

Speech-to-Text Module Type	Dataset	Model Type	Link
Speech Recogination	Aishell	DeepSpeech2 RNN + Conv based Models	deepspeech2-aishell
		Transformer based Attention Models	u2.transformer.conformer-aishell
	Librispeech	Transformer based Attention Models	deepspeech2-librispeech / transformer.conformer.u2-librispeech / transformer.conformer.u2-kaldi-librispeech
Alignment	THCHS30	MFA	mfa-thchs30
Language Model	Ngram Language Model		kenlm
	TIMIT	Unified Streaming & Non-streaming Two-pass	u2-timit
Speech Translation (English to Chinese)	TED En-Zh	Transformer + ASR MTL	transformer-ted
		FAT + Transformer + ASR MTL	fat-st-ted

Text-to-Speech in PaddleSpeech 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			tn / g2p
Acoustic Model	Tacotron2	LJSpeech	tacotron2-ljspeech
	Transformer TTS		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
	Multi Band MelGAN	CSMSC	Multi Band MelGAN-csmsc
Voice Cloning	GE2E	Librispeech, etc.	ge2e
	GE2E + Tactron2	AISHELL-3	ge2e-tactron2-aishell3
	GE2E + FastSpeech2	AISHELL-3	ge2e-fastspeech2-aishell3

Audio Classification

Task	Dataset	Model Type	Link
Audio Classification	ESC-50	PANN	pann-esc50

Documents

Normally, Speech SoTA, Audio SoTA and Music SoTA give you an overview of the hot academic topics in the related area. To focus on the tasks in PaddleSpeech, you will find the following guidelines are helpful to grasp the core ideas.

• Installation
• Quick Start
• Some Demos
• Tutorials
  • Automatic Speech Recognition
    • Introduction
    • Data Preparation
    • Data Augmentation
    • Ngram LM
  • Text-to-Speech
    • Introduction
    • Advanced Usage
    • Chinese Rule Based Text Frontend
    • Test Audio Samples
  • Audio Classification
  • Speech Translation
• Released Models
• Community
• Welcome to contribute
• licence

The Text-to-Speech module is originally called Parakeet, and now merged with this repository. If you are interested in academic research about this task, please see TTS research overview. Also, this document is a good guideline for the pipeline components.

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/PaddleSpeech}},
year={2021}
}

Contribute to PaddleSpeech

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

Contributors

Acknowledgement

• Many thanks to yeyupiaoling for years of attention, constructive advice and great help.
• Many thanks to AK391 for TTS web demo on Huggingface Spaces using Gradio.
• Many thanks to mymagicpower for the Java implementation of ASR upon short and long audio files.

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

License

PaddleSpeech is provided under the Apache-2.0 License.