Model reference · open weights

GigaAM-Multilingual

GigaAM-Multilingual is an open-weight audio or speech model from ai-sage, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Audio ai-sage 1 variants 117k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What GigaAM-Multilingual is

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. The models provide best-in-class open-source quality on Russian, Kazakh, Kyrgyz, and Uzbek, and moderate quality on English. GigaAM Multilingual includes the following model variants: - ssl — 220M self-supervised encoder - ctc — 220M ASR model with a character-wise CTC decoder - largessl — 600M self-supervised encoder - largectc — 600M ASR model with a character-wise CTC decoder Model Performance Word Error Rate (%) on Common Voice (CV), FLEURS, and internal in-the-wild test sets. Utterances longer than 30 s and references containing digits are excluded; references/hypotheses are normalized (lowercasing, punctuation removal, numerals→words); greedy decoding. Best per row in bold. Usage Recommended versions: - torch==2.10., torchaudio==2.10. - transformers==5. - (any) hydra-core, omegaconf Full usage guide can be found in the example. Fine-tuning to a new language The ssl / largessl backbones can be adapted to a new language — see the fine-tuning guide and the example notebook. Citation

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerai-sage
TypeAudio & music
Variants1
Released2026-07-14
Popularity117k downloads / month
Likes81
LicenceOpen weights

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
GigaAM-MultilingualBF16Weights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys gigaam-multilingual for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (gigaam-multilingual below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="gigaam-multilingual" -F file=@audio.mp3

Details

Languages, data & research

Languages

ru en kk ky uz

Tags

pytorch gigaam automatic-speech-recognition custom_code ru en kk ky uz

Papers

Licence

Open weights

Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want GigaAM-Multilingual on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More audio & music

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms