Model reference · open weights

whisper-ja

Available as managed deployment Audio efwkjn · community Speech→text 1 variants 520 dl/mo

whisper-ja is an open-weight audio or speech model from efwkjn. 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 byefwkjn
TypeAudio & music
TaskSpeech→text
Parameters (lead)1.5B
Released2026-02-13
Popularity520 downloads / month
LicenceUnknown

About

What whisper-ja is

For usage instructions follow openai/whisper-large-v3.

Large-v3 finetune trained as a baseline with smaller checkpoints in progress. Expecting worse long form and equal short form.

Benchmarks. Has occasional repetition issue compared to previous models but achieves competitive/SOTA CER across all tested sets.

Read the full model card

Acknowledgements

  • Train sets: OOPPEENN, Reazon, 小虫哥_, Common Voice 20, deepghs
  • Test sets: KitsuneX07, TEDxJP, kotoba-tech, Saruwatari-lab, grider-withourai

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-ja for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (whisper-ja 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-ja" -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