PaddleSpeech

(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.

PaddleSpeech won the NAACL2022 Best Demo Award, please check out our paper on Arxiv.

Speech Recognition

Speech Translation (English to Chinese)

Text-to-Speech

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

Punctuation Restoration

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, CLI, Server, and Streaming 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 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

• 🎉 2025.09.01: Add Whisper large v3 and turbo model.
• 🤗 2025.08.11: Add code-switch online model and server demo.
• 👑 2023.05.31: Add WavLM ASR-en, WavLM fine-tuning for ASR on LibriSpeech.
• 🎉 2023.05.18: Add Squeezeformer, Squeezeformer training for ASR on Aishell.
• 👑 2023.05.04: Add HuBERT ASR-en, HuBERT fine-tuning for ASR on LibriSpeech.
• ⚡ 2023.04.28: Fix 0-d tensor, with the upgrade of paddlepaddle==2.5, the problem of modifying 0-d tensor has been solved.
• 👑 2023.04.25: Add AMP for U2 conformer.
• 🔥 2023.04.06: Add subtitle file (.srt format) generation example.
• 🔥 2023.03.14: Add SVS(Singing Voice Synthesis) examples with Opencpop dataset, including DiffSinger、PWGAN and HiFiGAN, the effect is continuously optimized.
• 👑 2023.03.09: Add Wav2vec2ASR-zh.
• 🎉 2023.03.07: Add TTS ARM Linux C++ Demo (with C++ Chinese Text Frontend).
• 🔥 2023.03.03 Add Voice Conversion StarGANv2-VC synthesize pipeline.
• 🎉 2023.02.16: Add Cantonese TTS.
• 🔥 2023.01.10: Add code-switch asr CLI and Demos.
• 👑 2023.01.06: Add code-switch asr tal_cs recipe.
• 🎉 2022.12.02: Add end-to-end Prosody Prediction pipeline (including using prosody labels in Acoustic Model).
• 🎉 2022.11.30: Add TTS Android Demo.
• 🤗 2022.11.28: PP-TTS and PP-ASR demos are available in AIStudio and official website of paddlepaddle.
• 👑 2022.11.18: Add Whisper CLI and Demos, support multi language recognition and translation.
• 🔥 2022.11.18: Add Wav2vec2 CLI and Demos, Support ASR and Feature Extraction.
• 🎉 2022.11.17: Add male voice for TTS.
• 🔥 2022.11.07: Add U2/U2++ C++ High Performance Streaming ASR Deployment.
• 👑 2022.11.01: Add Adversarial Loss for Chinese English mixed TTS.
• 🔥 2022.10.26: Add Prosody Prediction for TTS.
• 🎉 2022.10.21: Add SSML for TTS Chinese Text Frontend.
• 👑 2022.10.11: Add Wav2vec2ASR-en, wav2vec2.0 fine-tuning for ASR on LibriSpeech.
• 🔥 2022.09.26: Add Voice Cloning, TTS finetune, and ERNIE-SAT in PaddleSpeech Web Demo.
• ⚡ 2022.09.09: Add AISHELL-3 Voice Cloning example with ECAPA-TDNN speaker encoder.
• ⚡ 2022.08.25: Release TTS finetune example.
• 🔥 2022.08.22: Add ERNIE-SAT models: ERNIE-SAT-vctk、ERNIE-SAT-aishell3、ERNIE-SAT-zh_en.
• 🔥 2022.08.15: Add g2pW into TTS Chinese Text Frontend.
• 🔥 2022.08.09: Release Chinese 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: Add PaddleSpeech Web Demo.
• 👑 2022.05.13: Release PP-ASR、PP-TTS、PP-VPR.
• 👏🏻 2022.05.06: PaddleSpeech Streaming Server is available for Streaming ASR with Punctuation Restoration and Token Timestamp and Text-to-Speech.
• 👏🏻 2022.05.06: PaddleSpeech Server is available for Audio Classification, Automatic Speech Recognition and Text-to-Speech, Speaker Verification and Punctuation Restoration.
• 👏🏻 2022.03.28: PaddleSpeech CLI is available for Speaker Verification.
• 👏🏻 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 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.

Installation

We strongly recommend our users to install PaddleSpeech in Linux with python>=3.8.

Dependency Introduction

• 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 of paddlepaddle 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 selection
pip install paddlepaddle==2.4.1 -i https://mirror.baidu.com/pypi/simple
# install develop version
pip 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

pip install pytest-runner
pip install paddlespeech

source code compilation

git clone https://github.com/PaddlePaddle/PaddleSpeech.git
cd PaddleSpeech
pip install pytest-runner
pip 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 this installation document. If you encounter problems during installation, you can leave a message on #2150 and find related problems

Quick Start

Developers can have a try of our models with PaddleSpeech 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.wav
wget -c https://paddlespeech.cdn.bcebos.com/PaddleAudio/en.wav

Automatic Speech Recognition

command line experience

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

Python API experience

>>> from paddlespeech.cli.asr.infer import ASRExecutor
>>> 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

Text-to-Speech

Output 24k sample rate wav format audio

command line experience

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

Python API experience

>>> from paddlespeech.cli.tts.infer import TTSExecutor
>>> tts = TTSExecutor()
>>> tts(text="今天天气十分不错。", output="output.wav")

• You can experience in Huggingface Spaces TTS Demo

Audio Classification

Sound classification model based on 527 categories of AudioSet dataset

command line experience

paddlespeech cls --input zh.wav

Python API experience

>>> from paddlespeech.cli.cls.infer import CLSExecutor
>>> cls = CLSExecutor()
>>> result = cls(audio_file="zh.wav")
>>> print(result)
Speech 0.9027186632156372

Voiceprint Extraction

command line experience

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

Python API experience

>>> from paddlespeech.cli.vector import VectorExecutor
>>> vec = VectorExecutor()
>>> result = vec(audio_file="zh.wav")
>>> print(result) # 187维向量
[ -0.19083306   9.474295   -14.122263    -2.0916545    0.04848729
   4.9295826    1.4780062    0.3733844   10.695862     3.2697146
  -4.48199     -0.6617882   -9.170393   -11.1568775   -1.2358263 ...]

Punctuation Restoration

command line experience

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

Python API experience

>>> from paddlespeech.cli.text.infer import TextExecutor
>>> 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。

Speech Translation

Use pre-compiled kaldi related tools, only support experience in Ubuntu system

command line experience

paddlespeech st --input en.wav

Python API experience

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

Quick Start Server

Developers can have a try of our speech server with PaddleSpeech 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

Quick Start Streaming Server

Developers can have a try of streaming asr and streaming 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 and streaming tts

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:

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

Audio Classification

Keyword Spotting

Speaker Verification

Speaker Diarization

Punctuation Restoration

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
    • 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 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.

⭐ Examples

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

• PaddleSpeech Demo Video

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

Citation

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}
}

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 HighCWu for adding VITS-aishell3 and VITS-VC examples.
• Many thanks to david-95 for fixing multi-punctuation bug、contributing to multiple program and data, and adding SSML for TTS Chinese Text Frontend.
• Many thanks to BarryKCL for improving TTS Chinses Frontend based on G2PW.
• Many thanks to yeyupiaoling/PPASR/PaddlePaddle-DeepSpeech/VoiceprintRecognition-PaddlePaddle/AudioClassification-PaddlePaddle for years of attention, constructive advice and great help.
• 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.
• Many thanks to phecda-xu/PaddleDubbing for developing a dubbing tool with GUI based on PaddleSpeech TTS model.
• Many thanks to jerryuhoo/VTuberTalk for developing a GUI tool based on PaddleSpeech TTS and code for making datasets from videos based on PaddleSpeech ASR.
• Many thanks to vpegasus/xuesebot for developing a rasa chatbot,which is able to speak and listen thanks to PaddleSpeech.
• Many thanks to chenkui164/FastASR for the C++ inference implementation of PaddleSpeech ASR.
• Many thanks to heyudage/VoiceTyping for the real-time voice typing tool implementation of PaddleSpeech ASR streaming services.
• Many thanks to EscaticZheng/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. See references for more information.
• Many thanks to chinobing/FastAPI-PaddleSpeech-Audio-To-Text for converting audio to text based on FastAPI and PaddleSpeech.
• Many thanks to MistEO/Pallas-Bot for QQ bot based on PaddleSpeech TTS.

License

PaddleSpeech is provided under the Apache-2.0 License.

Stargazers over time