Speech to text

Распознавание речи для башкирского, татарского и марийского (AigizK)

Years of work by one enthusiast around the Bashkir Common Voice project: Whisper, wav2vec2, w2v-BERT and GigaAM fine-tuned for Bashkir, Tatar and Mari. Quality differs between models, so test them on your own recordings.

Developer
Aigiz Kunafin (AigizK), member of the SLONE community, Russia
First release
Mar 2022
Latest release
Jul 2026
Sizes
from 220M to 1B across the different models
License
Commercial use with conditionsvaries by model: mostly Apache 2.0 and MIT, CC-BY-NC 4.0 for the Tatar model
Russian
Supported
Ready-made builds
8-bit
Running
On your own serverAlso runs without a GPU
Industries
Media and production, Public sector, Education, Customer support
Deploy on your server Hugging Face

What it does

  • Transcribing calls and meetings in Bashkir and Tatar
  • Subtitles for video and radio broadcasts
  • Turning archive recordings into text
  • Voice input in apps in a national language

Where it is used

Media and broadcastingGovernment and municipal bodiesEducation and culture

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. GigaAM Bashkir CV25 и сборка ONNX
  2. w2v-BERT 2.0 для марийского (Common Voice 17)
  3. MMS-1B для татарского, версия 2
  4. Whisper small для башкирского
  5. wav2vec2 XLS-R для башкирского (Common Voice 7)

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Распознавание речи для башкирского, татарского и марийского (AigizK) be used in a commercial project?

With conditions. License: varies by model: mostly Apache 2.0 and MIT, CC-BY-NC 4.0 for the Tatar model. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Распознавание речи для башкирского, татарского и марийского (AigizK) need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Распознавание речи для башкирского, татарского и марийского (AigizK) support Russian?

Yes, Russian is listed on the model card.

Where can I download Распознавание речи для башкирского, татарского и марийского (AigizK) and what does it cost?

The Распознавание речи для башкирского, татарского и марийского (AigizK) weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Speech to textWhisperOpenAI · USACommercial use allowed

Speech recognition in 99 languages, including Russian. The de facto standard for transcribing calls and meetings. Hugging Face's faster Distil-Whisper is English only.

DetailsSpeech to textGigaAMSber · RussiaCommercial use allowed

Sber's models for Russian speech recognition, among the most accurate for Russian. Includes emotion recognition, v3 with punctuation, and a multilingual version (Russian, Kazakh, Kyrgyz, Uzbek).

DetailsSpeech to textVosk (русские модели)Alpha Cephei · RussiaCommercial use allowed

Offline Russian speech recognition that runs even on a Raspberry Pi or a phone, without internet. Streaming models for live audio and simple Russian speech synthesis, Vosk TTS, are available.

Details

Source: huggingface.co/AigizK/GigaAM-Bashkir-CV25. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.