#2626th of 26 in Voice
paddlespeech
Speech toolkit on PaddlePaddle for ASR, TTS, translation and speaker verification
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 12.7k
- License
- Apache-2.0
- Last commit
- Jun 2026
- Last release
- Mar 2025
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
PaddleSpeech is a Python toolkit built on PaddlePaddle that covers speech recognition, text-to-speech, English-to-Chinese speech translation, speaker verification, audio classification and punctuation restoration. It provides a CLI, a Python API, and a server and streaming server (the client example uses port 8090). It includes a rule-based Chinese text frontend and training recipes for datasets such as LibriSpeech, AISHELL and CSMSC.
Who it is for: Engineers needing self-hosted ASR/TTS, especially Chinese, or speech researchers
Strengths
- One toolkit covers ASR, TTS, speech translation, speaker verification, audio classification and punctuation
- Streaming ASR and TTS servers, plus C++ U2/U2++ streaming ASR deployment
- Rule-based Chinese text normalization and G2P; Cantonese and Chinese-English mixed TTS
- All TTS models support ONNX; CPU install is documented
Weaknesses
- Requires PaddlePaddle, a smaller ecosystem than PyTorch
- Speech translation supports only English to Chinese and is documented for Ubuntu only
- Last release was 2025-03-05, though commits continue
- No Docker image or compose file; install is via pip or source build
What it needs
- GPU optional
- Needs paddlepaddle, python>=3.8, gcc>=4.8.5
- Models: Whisper large v3 and turbo, wav2vec2, HuBERT, WavLM, U2/U2++ conformer
- port 8090
Also in Voice
See all 26| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing and dictation with local speech models | 82 out of 100 |
| 2 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 76 out of 100 |
| 3 | buzzOffline desktop app for transcribing and translating audio with Whisper | 74 out of 100 |
| #4 | VoiceboxLocal voice studio for cloning, TTS, dictation and agent speech | 70 out of 100 |
| #5 | meetilyDesktop app that records, transcribes and summarizes meetings locally | 66 out of 100 |