# Speech and audio models | SAVRN Model Hub
Source: https://savrn.com/collections/speech-and-audio
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Entries in this collection

Model · Speech recognition

### [whisper-large-v3](https://savrn.com/models/whisper-large-v3)

Published by [OpenAI](https://savrn.com/model-publishers/openai)

Why it is here: Speech recognition across many languages.

Open weights apache-2.0 1.5B parameters

[View model](https://savrn.com/models/whisper-large-v3)

Model · Speech recognition

### [whisper-small](https://savrn.com/models/whisper-small)

Published by [OpenAI](https://savrn.com/model-publishers/openai)

Why it is here: The smaller Whisper, for constrained hardware.

Open weights apache-2.0 242M parameters

[View model](https://savrn.com/models/whisper-small)

Model · Speech recognition

### [speaker-diarization-3.1](https://savrn.com/models/speaker-diarization-3-1)

Published by [Pyannote](https://savrn.com/model-publishers/pyannote)

Why it is here: Speaker diarization, gated by its publisher.

Access requested at publisher mit

[View model](https://savrn.com/models/speaker-diarization-3-1)

[Compare the first 3 models in this collection](https://savrn.com/models/compare?ids=whisper-large-v3,whisper-small,speaker-diarization-3-1)

## Explore More

[Every collection](https://savrn.com/collections) · [The model directory](https://savrn.com/models) · [How a collection is decided](https://savrn.com/model-hub/methodology)