Model reference · open weights
speaker-diarization-3.0 is an open-weight audio or speech model from pyannote, 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.
Specifications
| Maker | pyannote |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | pyannote-audio |
| Released | 2023-09-22 |
| Popularity | 205k downloads / month |
| Likes | 223 |
| Licence | Open weights |
How it works
Variants
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.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| speaker-diarization-3.0 | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys speaker-diarization-3-0 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (speaker-diarization-3-0 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="speaker-diarization-3-0" -F file=@audio.mp3
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗