#116 · Primary category: Speech & Audio
pykaldi
A Python wrapper for Kaldi
Project last updated:11/30/25
GitHub Stars
1.0K
Forks
247
Contributors
32
License
Apache-2.0
Why we included this project
Kaldi is powerful but C++-heavy, and PyKaldi exists to close that gap: it wraps both Kaldi and OpenFst so you can call low-level functions, inspect and modify recognizer internals, and write new tools without dropping back into C++. The people who get the most out of it are researchers and engineers already committed to Kaldi who want programmatic control over its guts. If that sounds like more than you need, the asr, alignment, and segmentation modules provide a gentler path for developers who just want to run a pre-trained Kaldi pipeline inside a larger Python application. PyKaldi deliberately does not try to replicate Kaldi's command-line recipes; it is meant to sit beside an existing Kaldi setup and extend it. That makes it a practical fit for teams that want to escape the C++ layer without rebuilding their stack.
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