Model reference · open weights
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 by | efwkjn |
|---|---|
| Type | Audio & music |
| Task | Speech→text |
| Parameters (lead) | 1.5B |
| Released | 2026-02-13 |
| Popularity | 520 downloads / month |
| Licence | Unknown |
About
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.
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
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.