(简体中文|English)
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.
| 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。 |
| Input Audio | Translations Result |
|---|---|
|
|
我 在 这栋 建筑 的 古老 门上 敲门。 |
| 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。 |
|
| 季姬寂，集鸡，鸡即棘鸡。棘鸡饥叽，季姬及箕稷济鸡。鸡既济，跻姬笈，季姬忌，急咭鸡，鸡急，继圾几，季姬急，即籍箕击鸡，箕疾击几伎，伎即齑，鸡叽集几基，季姬急极屐击鸡，鸡既殛，季姬激，即记《季姬击鸡记》。 |
|
For more synthesized audios, please refer to PaddleSpeech Text-to-Speech samples.
| Input Text | Output Text |
|---|---|
| 今天的天气真不错啊你下午有空吗我想约你一起去吃饭 | 今天的天气真不错啊！你下午有空吗？我想约你一起去吃饭。 |
- PaddleBoBo: Use PaddleSpeech TTS to generate virtual human voice.
-
2021.12.21~12.24
4 Days Live Courses: Depth interpretation of PaddleSpeech!
Courses videos and related materials: https://aistudio.baidu.com/aistudio/education/group/info/25130
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).
- 🤗 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.
- Scan the QR code below with your Wechat (reply【语音】after your friend's application is approved), you can access to official technical exchange group. Look forward to your participation.
We strongly recommend our users to install PaddleSpeech in Linux with python>=3.7.
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. To install PaddleSpeech, please see installation.
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.wavAutomatic Speech Recognition
paddlespeech asr --lang zh --input input_16k.wavSpeech Translation (English to Chinese) (not support for Mac and Windows now)
paddlespeech st --input input_16k.wavText-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
Text Postprocessing
- Punctuation Restoration
paddlespeech text --task punc --input 今天的天气真不错啊你下午有空吗我想约你一起去吃饭
<
8000
/ul>
- ASR + Punctuation Restoration
- Installation
- Quick Start
- Some Demos
- Tutorials
- Released Models
- Community
- Welcome to contribute
- License
- Many thanks to yeyupiaoling/PPASR/PaddlePaddle-DeepSpeech/VoiceprintRecognition-PaddlePaddle/AudioClassification-PaddlePaddle 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.
- Many thanks to JiehangXie/PaddleBoBo for developing Virtual Uploader(VUP)/Virtual YouTuber(VTuber) with PaddleSpeech TTS function.
- Many thanks to 745165806/PaddleSpeechTask for contributing Punctuation Restoration model.
- Many thanks to kslz for supplementary Chinese documents.
- Many thanks to awmmmm for contributing fastspeech2 aishell3 conformer pretrained model.
Batch Process
echo -e "1 欢迎光临。\n2 谢谢惠顾。" | paddlespeech tts
Shell Pipeline
paddlespeech asr --input ./zh.wav | paddlespeech text --task punc
For more command lines, please see: demos
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.
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 | |
| TIMIT | Unified Streaming & Non-streaming Two-pass | u2-timit | |
| Alignment | THCHS30 | MFA | mfa-thchs30 |
| Language Model | Ngram Language Model | kenlm | |
| 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 / CSMSC | tacotron2-ljspeech / tacotron2-csmsc |
| Transformer TTS | LJSpeech | transformer-ljspeech | |
| SpeedySpeech | CSMSC | speedyspeech-csmsc | |
| FastSpeech2 | LJSpeech / VCTK / CSMSC / AISHELL-3 | fastspeech2-ljspeech / fastspeech2-vctk / fastspeech2-csmsc / fastspeech2-aishell3 | |
| Vocoder | WaveFlow | LJSpeech | waveflow-ljspeech |
| Parallel WaveGAN | LJSpeech / VCTK / CSMSC / AISHELL-3 | PWGAN-ljspeech / PWGAN-vctk / PWGAN-csmsc / PWGAN-aishell3 | |
| Multi Band MelGAN | CSMSC | Multi Band MelGAN-csmsc | |
| Style MelGAN | CSMSC | Style MelGAN-csmsc | |
| HiFiGAN | CSMSC | HiFiGAN-csmsc | |
| WaveRNN | CSMSC | WaveRNN-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 |
Punctuation Restoration
| Task | Dataset | Model Type | Link |
|---|---|---|---|
| Punctuation Restoration | IWLST2012_zh | Ernie Linear | iwslt2012-punc0 |
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.
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.
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}
}
@inproceedings{zheng2021fused,
title={Fused acoustic and text encoding for multimodal bilingual pretraining and speech translation},
author={Zheng, Renjie and Chen, Junkun and Ma, Mingbo and Huang, Liang},
booktitle={International Conference on Machine Learning},
pages={12736--12746},
year={2021},
organization={PMLR}
}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!
Besides, PaddleSpeech depends on a lot of open source repositories. See references for more information.
PaddleSpeech is provided under the Apache-2.0 License.