Vosk

Vosk is an open-source speech recognition toolkit by Alphacephei. Key features are:

1. Supports 20+ languages and dialects - English, Indian English, German, French, Spanish, Portuguese, Chinese, Russian, Turkish, Vietnamese, Italian, Dutch, Catalan, Arabic, Greek, Farsi, Filipino, Ukrainian, Kazakh, Swedish. More to come.
2. Works offline, even on lightweight devices - Raspberry Pi, Android, iOS
3. Installs with simple pip3 install vosk
4. Portable per-language models are only 50Mb each, but there are much bigger server models available.
5. Provides streaming API for the best user experience (unlike popular speech-recognition python packages)
6. There are bindings for different programming languages, too - java/csharp/javascript etc.
7. Allows quick reconfiguration of vocabulary for best accuracy.
8. Supports speaker identification beside simple speech recognition.

Vosk related projects

- https://github.com/solyarisoftware/voskjs Vosk ASR offline engine API for NodeJs developers. With a simple HTTP ASR server