This model requires you to accept the MIT license terms before download.
Description
Whisper Large-V2 — OpenAI's multilingual speech-to-text model for robust transcription and translation across 99 languages, resilient to accents and background noise. Relabeled 2026-08-26: this artifact was previously listed as Large-V3; fingerprint verification (80 mel bins, 99 language tokens) identified it as large-v2-class. MIT license.
Tags
At a glance
| Kind | speech-to-text model |
|---|---|
| Precision | float32 |
| Container size | 5.8 GiB |
| Weights inside | 5.7 GiB |
| Components | 2 |
| Licence | MIT |
What is inside the container
A .nbx container packs every part of whisper-large — 2 components with weights, graphs and runtime settings — so one file is all the runtime needs.
| Component | Blocks | Layers | Weights |
|---|---|---|---|
| model.decoder | 0 | 32 | 3.4 GiB |
| model.encoder | 0 | — | 2.4 GiB |
Default settings
The values the container ships with. They apply when you do not pass your own.
- Temperature
- 0
Memory needed
The weights of whisper-large take 5.7 GiB in float32. That is the floor for the memory the runtime has to place, spread over the devices it finds; activations come on top and grow with the size and length you ask for. A measured peak per device class is not published for this model yet.
Verify what you downloaded
Every download carries its SHA-256, and the file endpoint sends it in the X-NBX-SHA256 header. The container is 5.8 GiB (6,174,992,983 bytes).
$ sha256sum whisper-large.nbx
8e191e54a5b836f2a0539faad90781e0142712449103413d88f9ba1927f60511
Questions
What is whisper-large?
A speech-to-text model by openai, distributed as a float32 .nbx container and licensed MIT.
How big is the download?
5.8 GiB, of which 5.7 GiB are weights.
How do I run it?
Install the runtime from the download page, then use the commands under “CLI Usage” below: neurobrix import openai/whisper-large, then neurobrix serve --model whisper-large.
CLI Usage
$ neurobrix import openai/whisper-large
$ neurobrix serve --model whisper-large
$ neurobrix run --prompt "your prompt here"
$ neurobrix stop