Model reference · open weights

whisper-tiny-lv

Available as managed deployment Audio RaivisDejus · community Speech→text 1 variants 644 dl/mo

whisper-tiny-lv is an open-weight audio or speech model from RaivisDejus. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byRaivisDejus
TypeAudio & music
TaskSpeech→text
Parameters (lead)38M
Runs withtransformers
Released2024-04-28
Popularity644 downloads / month
LicenceOpen weights

About

What whisper-tiny-lv is

Trained on combination of:

  • Common Voice 17, custom selection of all validated clips, max 1000 clips per speaker
  • Fleurs, test+train+validation

Both regular whisper model and CTranslate2 converted version for use with faster-whisper as part of Home Assistant Whisper integration are available.

Speech recognition quality is poor, more data is needed, donate your voice on Balsu talka

For better recognition quality use whisper-small-lv model, it is noticeably better and only slightly slower.

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys whisper-tiny-lv for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (whisper-tiny-lv 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="whisper-tiny-lv" -F file=@audio.mp3

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

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