#20 · Primary category： Speech & Audio
PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
Project last updated：08/12/26
GitHub Stars
12.7K
Forks
2.0K
Contributors
163
License
Apache-2.0
Why we included this project
PaddleSpeech packs a lot of speech work into one PaddlePaddle-based codebase: automatic speech recognition, text-to-speech, speaker verification, keyword spotting, and speech translation. For teams shipping real products rather than evaluating a single model, the streaming ASR and streaming TTS servers are the practical part, and the rule-based Chinese text frontend handles text normalization and grapheme-to-phoneme conversion without much fiddling. Multilingual and code-switching needs are covered by ready-made recipes for datasets like LibriSpeech, AIShell, and CSMSC, with newer Whisper and WavLM integrations for recognition. It also includes demos for subtitle generation, mobile TTS, and ARM Linux deployment, which shortens the path from experiment to a running service. The NAACL2022 best demo award is a reasonable signal that the toolkit is genuinely usable.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
whisper.cpp
Port of OpenAI's Whisper model in C/C++
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
VibeVoice
Open-Source Frontier Voice AI
voicebox
The open-source AI voice studio. Clone, dictate, create.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production