salute-developers/GigaAM

Foundational Model for Speech Recognition Tasks

73
/ 100
Verified

GigaAM is a collection of powerful speech recognition and emotion detection models primarily designed for the Russian language. It takes spoken audio as input and can transcribe it into text, including punctuation and word-level timestamps, or identify emotions expressed in the speech. This tool is ideal for developers and researchers working on applications involving Russian voice assistants, call center analytics, or content transcription.

504 stars. Actively maintained with 9 commits in the last 30 days. Available on PyPI.

Use this if you need highly accurate speech-to-text transcription or emotion recognition for Russian-language audio, especially for challenging or diverse speech datasets.

Not ideal if your primary need is for languages other than Russian, or if you are looking for a ready-to-use application rather than a foundational model to integrate into a system.

speech-to-text voice-processing call-center-analytics emotion-recognition Russian-language
Maintenance 17 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

504

Forks

76

Language

Python

License

MIT

Last pushed

Feb 12, 2026

Commits (30d)

9

Dependencies

10

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/salute-developers/GigaAM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.