GigaAM-Multilingual
GigaAM Multilingual is a family of Conformer-based foundation models (220M / 600M parameters) pre-trained with a HuBERT-style objective on 2M hours of speech across 70+ languages and fine-tuned for speech recognition with character-wise CTC decoders on 50K hours.
audio → text · made by ai-sage
Sold by
Nobody in the catalogue publishes a price for this yet.
About
GigaAM-Multilingual — a text model from ai-sage.
It takes audio and returns text. It was published in July 2026. The catalogue files it under transcribe. Its weights are published under MIT, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- ai-sage
- Register
- model
- Takes
- audio
- Returns
- text
- Published
- July 2026
- Licence
- mit
Known as 1 name
ai-sage/GigaAM-Multilingual