Model reference · open weights
whisper-large-ov is an open-weight audio or speech model from OpenVINO, 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.
About
whisper-large-v3-turbo-int8-ov Model creator: OpenAI Original model: whisper-large-v3-turbo Description This is whisper-large-v3-turbo model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT8 by NNCF. Whisper large-v3-turbo is a finetuned version of a pruned Whisper large-v3 with the number of decoder layers reduced from 32 to 4, which makes the model significantly faster at the expense of a minor quality degradation. Quantization Parameters Weight compression was performed using nncf.compressweights with the following parameters: mode: INT8ASYM groupsize: 128 For more information on quantization, check the OpenVINO model optimization guide. Compatibility The provided OpenVINO™ IR model is compatible with: OpenVINO version 2026.1.0 and higher Optimum Intel 1.27.0 and higher Running Model Inference with Optimum Intel 1. Install packages required for using Optimum Intel integration with the OpenVINO backend: 2. Run model inference: Running Model Inference with OpenVINO GenAI 1. Install packages required for using OpenVINO GenAI. 2. Download model from HuggingFace Hub 3. Run model inference: More GenAI usage examples can be found in OpenVINO GenAI library docs and samples Running Model with OpenAI client and OpenVINO Model Server 1a. Deploy model on Windows using binary package: 1b. Deploy model in a Docker container: 2. Install the client library: 3. Run the client: Limitations Check the original model card for original model card for limitations. Legal information The original model is distributed under MIT license. More details can be found in original model card. Disclaimer Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See Intel’s Global Human Rights Principles. Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | OpenVINO |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Based on | openai/whisper-large-v3-turbo |
| Released | 2026-05-13 |
| Popularity | 1k downloads / month |
| Likes | 2 |
| 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 |
|---|---|---|---|---|---|
| whisper-large-v3-turbo-int8-ov | — | INT8 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys whisper-large-ov for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (whisper-large-ov 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-large-ov" -F file=@audio.mp3
Details
Languages
Tags
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗