Repository files navigation

(简体中文|English)

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

PaddleSpeech won theNAACL2022 Best Demo Award, please check out our paper onArxiv.

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》。
大家好，我是 parrot 虚拟老师，我们来读一首诗，我与春风皆过客，I and the spring breeze are passing by，你携秋水揽星河，you take the autumn water to take the galaxy。
宜家唔系事必要你讲，但系你所讲嘅说话将会变成呈堂证供。
各个国家有各个国家嘅国歌

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

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,CLI,Server, andStreaming Server 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.
• 🏆Streaming ASR and TTS System: we provide production ready streaming asr and streaming tts system.
• 💯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 Automatic Speech Recognition, Text-to-Speech Synthesis, Speaker Verification, KeyWord Spotting, Audio Classification, and Speech Translation, 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 alsomodel 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).

• 👑 2023.05.31: AddWavLM ASR-en, WavLM fine-tuning for ASR on LibriSpeech.
• 🎉 2023.05.18: AddSqueezeformer, Squeezeformer training for ASR on Aishell.
• 👑 2023.05.04: AddHuBERT ASR-en, HuBERT fine-tuning for ASR on LibriSpeech.
• ⚡ 2023.04.28: Fix0-d tensor, with the upgrade of paddlepaddle==2.5, the problem of modifying 0-d tensor has been solved.
• 👑 2023.04.25: AddAMP for U2 conformer.
• 🔥 2023.04.06: Addsubtitle file (.srt format) generation example.
• 🔥 2023.03.14: Add SVS(Singing Voice Synthesis) examples with Opencpop dataset, includingDiffSinger、PWGAN andHiFiGAN, the effect is continuously optimized.
• 👑 2023.03.09: AddWav2vec2ASR-zh.
• 🎉 2023.03.07: AddTTS ARM Linux C++ Demo (with C++ Chinese Text Frontend).
• 🔥 2023.03.03 Add Voice ConversionStarGANv2-VC synthesize pipeline.
• 🎉 2023.02.16: AddCantonese TTS.
• 🔥 2023.01.10: Addcode-switch asr CLI and Demos.
• 👑 2023.01.06: Addcode-switch asr tal_cs recipe.
• 🎉 2022.12.02: Addend-to-end Prosody Prediction pipeline (including using prosody labels in Acoustic Model).
• 🎉 2022.11.30: AddTTS Android Demo.
• 🤗 2022.11.28: PP-TTS and PP-ASR demos are available inAIStudio andofficial websiteof paddlepaddle.
• 👑 2022.11.18: AddWhisper CLI and Demos, support multi language recognition and translation.
• 🔥 2022.11.18: AddWav2vec2 CLI and Demos, Support ASR and Feature Extraction.
• 🎉 2022.11.17: Addmale voice for TTS.
• 🔥 2022.11.07: AddU2/U2++ C++ High Performance Streaming ASR Deployment.
• 👑 2022.11.01: AddAdversarial Loss forChinese English mixed TTS.
• 🔥 2022.10.26: AddProsody Prediction for TTS.
• 🎉 2022.10.21: AddSSML for TTS Chinese Text Frontend.
• 👑 2022.10.11: AddWav2vec2ASR-en, wav2vec2.0 fine-tuning for ASR on LibriSpeech.
• 🔥 2022.09.26: Add Voice Cloning, TTS finetune, andERNIE-SAT inPaddleSpeech Web Demo.
• ⚡ 2022.09.09: Add AISHELL-3 Voice Cloningexample with ECAPA-TDNN speaker encoder.
• ⚡ 2022.08.25: Release TTSfinetune example.
• 🔥 2022.08.22: AddERNIE-SAT models:ERNIE-SAT-vctk、ERNIE-SAT-aishell3、ERNIE-SAT-zh_en.
• 🔥 2022.08.15: Addg2pW into TTS Chinese Text Frontend.
• 🔥 2022.08.09: ReleaseChinese English mixed TTS.
• ⚡ 2022.08.03: Add ONNXRuntime infer for TTS CLI.
• 🎉 2022.07.18: Release VITS:VITS-csmsc、VITS-aishell3、VITS-VC.
• 🎉 2022.06.22: All TTS models support ONNX format.
• 🍀 2022.06.17: AddPaddleSpeech Web Demo.
• 👑 2022.05.13: ReleasePP-ASR、PP-TTS、PP-VPR.
• 👏🏻 2022.05.06:PaddleSpeech Streaming Server is available forStreaming ASR withPunctuation Restoration andToken Timestamp andText-to-Speech.
• 👏🏻 2022.05.06:PaddleSpeech Server is available forAudio Classification,Automatic Speech Recognition andText-to-Speech,Speaker Verification andPunctuation Restoration.
• 👏🏻 2022.03.28:PaddleSpeech CLI is available forSpeaker Verification.
• 👏🏻 2021.12.10:PaddleSpeech CLI is available forAudio Classification,Automatic Speech Recognition,Speech Translation (English to Chinese) andText-to-Speech.

• Scan the QR code below with your Wechat, you can access to official technical exchange group and get the bonus ( more than 20GB learning materials, such as papers, codes and videos ) and the live link of the lessons. Look forward to your participation.

We strongly recommend our users to install PaddleSpeech inLinux withpython>=3.8.

• gcc >= 4.8.5
• paddlepaddle
• python >= 3.8
• OS support: Linux(recommend), Windows, Mac OSX

PaddleSpeech depends on paddlepaddle. For installation, please refer to the official website ofpaddlepaddle and choose according to your own machine. Here is an example of the cpu version.

pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple

You can also specify the version of paddlepaddle or install the develop version.

# install 2.4.1 version. Note, 2.4.1 is just an example, please follow the minimum dependency of paddlepaddle for your selectionpip install paddlepaddle==2.4.1 -i https://mirror.baidu.com/pypi/simple# install develop versionpip install paddlepaddle==0.0.0 -f https://www.paddlepaddle.org.cn/whl/linux/cpu-mkl/develop.html

There are two quick installation methods for PaddleSpeech, one is pip installation, and the other is source code compilation (recommended).

pip install pytest-runnerpip install paddlespeech

git clone https://github.com/PaddlePaddle/PaddleSpeech.gitcd PaddleSpeechpip install pytest-runnerpip install.# If you need to install in editable mode, you need to use --use-pep517. The command is as follows:# pip install -e . --use-pep517

For more installation problems, such as conda environment, librosa-dependent, gcc problems, kaldi installation, etc., you can refer to thisinstallation document. If you encounter problems during installation, you can leave a message on#2150 and find related problems

Developers can have a try of our models withPaddleSpeech Command Line or Python. Change--input to test your own audio/text and support 16k wav format audio.

You can also quickly experience it in AI Studio 👉🏻PaddleSpeech API Demo

Test audio sample download

wget -c https://paddlespeech.cdn.bcebos.com/PaddleAudio/zh.wavwget -c https://paddlespeech.cdn.bcebos.com/PaddleAudio/en.wav

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

>>>frompaddlespeech.cli.asr.inferimportASRExecutor>>>asr=ASRExecutor()>>>result=asr(audio_file="zh.wav")>>>print(result)我认为跑步最重要的就是给我带来了身体健康

paddlespeech tts --input"你好，欢迎使用百度飞桨深度学习框架！" --output output.wav

>>>frompaddlespeech.cli.tts.inferimportTTSExecutor>>>tts=TTSExecutor()>>>tts(text="今天天气十分不错。",output="output.wav")

paddlespeech cls --input zh.wav

>>>frompaddlespeech.cli.cls.inferimportCLSExecutor>>>cls=CLSExecutor()>>>result=cls(audio_file="zh.wav")>>>print(result)Speech0.9027186632156372

paddlespeech vector --task spk --input zh.wav

>>>frompaddlespeech.cli.vectorimportVectorExecutor>>>vec=VectorExecutor()>>>result=vec(audio_file="zh.wav")>>>print(result)# 187维向量[-0.190833069.474295-14.122263-2.09165450.048487294.92958261.47800620.373384410.6958623.2697146-4.48199-0.6617882-9.170393-11.1568775-1.2358263 ...]

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

>>>frompaddlespeech.cli.text.inferimportTextExecutor>>>text_punc=TextExecutor()>>>result=text_punc(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。

paddlespeech st --input en.wav

>>>frompaddlespeech.cli.st.inferimportSTExecutor>>>st=STExecutor()>>>result=st(audio_file="en.wav")['我 在 这栋 建筑 的 古老 门上 敲门 。']

Developers can have a try of our speech server withPaddleSpeech Server Command Line.

You can try it quickly in AI Studio (recommend):SpeechServer

Start server

paddlespeech_server start --config_file ./demos/speech_server/conf/application.yaml

Access Speech Recognition Services

paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input input_16k.wav

Access Text to Speech Services

paddlespeech_client tts --server_ip 127.0.0.1 --port 8090 --input"您好，欢迎使用百度飞桨语音合成服务。" --output output.wav

Access Audio Classification Services

paddlespeech_client cls --server_ip 127.0.0.1 --port 8090 --input input.wav

For more information about server command lines, please see:speech server demos

Developers can have a try ofstreaming asr andstreaming tts server.

Start Streaming Speech Recognition Server

paddlespeech_server start --config_file ./demos/streaming_asr_server/conf/application.yaml

Access Streaming Speech Recognition Services

paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8090 --input input_16k.wav

Start Streaming Text to Speech Server

paddlespeech_server start --config_file ./demos/streaming_tts_server/conf/tts_online_application.yaml

Access Streaming Text to Speech Services

paddlespeech_client tts_online --server_ip 127.0.0.1 --port 8092 --protocol http --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav

For more information please see:streaming asr andstreaming tts

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

Speech-to-Text containsAcoustic Model,Language Model, andSpeech Translation, with the following details:

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

Audio Classification

Keyword Spotting

Speaker Verification

Speaker Diarization

Punctuation Restoration

Normally,Speech SoTA,Audio SoTA andMusic 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
    • Ngram LM
  • Text-to-Speech
    • Introduction
    • Advanced Usage
    • Chinese Rule Based Text Frontend
    • Test Audio Samples
  • Speaker Verification
    • Audio Searching
    • Speaker Verification
  • Audio Classification
  • Speech Translation
  • Speech Server
• Released Models
  • Speech-to-Text
  • Text-to-Speech
  • Audio Classification
  • Speaker Verification
  • Speaker Diarization
  • Punctuation Restoration
• Community
• Welcome to contribute
• License

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

• PaddleBoBo: Use PaddleSpeech TTS to generate virtual human voice.

• PaddleSpeech Demo Video

• VTuberTalk: Use PaddleSpeech TTS and ASR to clone voice from videos.

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

@inproceedings{zhang2022paddlespeech,    title = {PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit},    author = {Hui Zhang, Tian Yuan, Junkun Chen, Xintong Li, Renjie Zheng, Yuxin Huang, Xiaojie Chen, Enlei Gong, Zeyu Chen, Xiaoguang Hu, dianhai yu, Yanjun Ma, Liang Huang},    booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations},    year = {2022},    publisher = {Association for Computational Linguistics},}@InProceedings{pmlr-v162-bai22d,  title = {{A}$^3${T}: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing},  author = {Bai, He and Zheng, Renjie and Chen, Junkun and Ma, Mingbo and Li, Xintong and Huang, Liang},  booktitle = {Proceedings of the 39th International Conference on Machine Learning},  pages = {1399--1411},  year = {2022},  volume = {162},  series = {Proceedings of Machine Learning Research},  month = {17--23 Jul},  publisher = {PMLR},  pdf = {https://proceedings.mlr.press/v162/bai22d/bai22d.pdf},  url = {https://proceedings.mlr.press/v162/bai22d.html},}@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 indiscussions and bug reports inissues! Also, we highly appreciate if you are willing to contribute to this project!

• Many thanks toHighCWu for addingVITS-aishell3 andVITS-VC examples.
• Many thanks todavid-95 for fixing multi-punctuation bug、contributing to multiple program and data, and addingSSML for TTS Chinese Text Frontend.
• Many thanks toBarryKCL for improving TTS Chinses Frontend based onG2PW.
• Many thanks toyeyupiaoling/PPASR/PaddlePaddle-DeepSpeech/VoiceprintRecognition-PaddlePaddle/AudioClassification-PaddlePaddle for years of attention, constructive advice and great help.
• Many thanks tomymagicpower for the Java implementation of ASR uponshort andlong audio files.
• Many thanks toJiehangXie/PaddleBoBo for developing Virtual Uploader(VUP)/Virtual YouTuber(VTuber) with PaddleSpeech TTS function.
• Many thanks to745165806/PaddleSpeechTask for contributing Punctuation Restoration model.
• Many thanks tokslz for supplementary Chinese documents.
• Many thanks toawmmmm for contributing fastspeech2 aishell3 conformer pretrained model.
• Many thanks tophecda-xu/PaddleDubbing for developing a dubbing tool with GUI based on PaddleSpeech TTS model.
• Many thanks tojerryuhoo/VTuberTalk for developing a GUI tool based on PaddleSpeech TTS and code for making datasets from videos based on PaddleSpeech ASR.
• Many thanks tovpegasus/xuesebot for developing a rasa chatbot,which is able to speak and listen thanks to PaddleSpeech.
• Many thanks tochenkui164/FastASR for the C++ inference implementation of PaddleSpeech ASR.
• Many thanks toheyudage/VoiceTyping for the real-time voice typing tool implementation of PaddleSpeech ASR streaming services.
• Many thanks toEscaticZheng/ps3.9wheel-install for the python3.9 prebuilt wheel for PaddleSpeech installation in Windows without Visual Studio.Besides, PaddleSpeech depends on a lot of open source repositories. Seereferences for more information.
• Many thanks tochinobing/FastAPI-PaddleSpeech-Audio-To-Text for converting audio to text based on FastAPI and PaddleSpeech.
• Many thanks toMistEO/Pallas-Bot for QQ bot based on PaddleSpeech TTS.

PaddleSpeech is provided under theApache-2.0 License.