USASI
Model release

Whisper large-v3

Release in the Whisper family · version large-v3

Maintained by OpenAI43

Whisper large-v3 is a 1550M-parameter multilingual speech recognition and translation model released by OpenAI in November 2023. It keeps the architecture of the earlier large models but uses 128 Mel frequency bins instead of 80 and adds a language token for Cantonese.314

Last reviewedEntry updated Documented release Nov 6, 2023

Availability and license

Overall availability

Public

Downloadable without gating from Hugging Face, and fetched automatically by the openai-whisper package when "large-v3" (or its alias "large") is loaded.273

Availability is separate from permission: read the license before using or redistributing.

The sources disagree. The openai/whisper README states that Whisper's code and model weights are released under the MIT License, while the Hugging Face repository for large-v3 declares Apache-2.0 in its card metadata. Both are permissive licenses; this catalog records both rather than choosing one.51

Model-disclosure tier

Computed from the checklist below using USASI rubric v0.1. An editorial category, not a certification.
Model-disclosure tier (USASI rubric v0.1): Open-weight

The model parameters for this release can be downloaded by the public. License terms may still restrict use, redistribution, or commercial use.

How tiers are computed

Public materials checklist

Items for a model under USASI rubric v0.1. Unknown means unassessed or insufficient evidence.
Public materials checklist for Whisper large-v3
ItemStatusNotes and evidence
WeightsCan the general public download the model parameters for this release?PublicPublished on Hugging Face without gating and downloadable through the openai-whisper package.27
Inference codeIs code for running the model published?PublicThe openai/whisper repository provides the inference code and command-line tool; the Hugging Face card documents inference with Transformers.51
Training codeIs the code used to train the model published?UnknownThe repository covers inference and evaluation-data preparation; this review found no published training code.5
Training-data informationPublic = the training data itself can be obtained. Partial = composition or sources are documented without full access.PartialTrained on 1 million hours of weakly labeled audio and 4 million hours of audio pseudo-labeled with large-v2. The data is described but not released.31
Training recipeAre the training configuration and procedure documented in enough detail to follow?PartialOpenAI states the model was trained for 2.0 epochs over this mixture and lists the architectural changes from large-v2; the original paper describes the general training approach. No training configuration is published.39
Evaluation materialsPublic = evaluation code or prompts that let others re-run the evaluations are published. Partial = results only.PartialThe README and release discussion report word and character error rates for large-v3 on Common Voice 15 and FLEURS. The repository documents how the paper's evaluation datasets were prepared, but no large-v3 evaluation scripts were located.538

What it is useful for

Multilingual transcription and translation of speech into English. The model card names AI researchers as the primary intended users, says the models may also serve developers as a speech recognition solution, and advises against non-consensual transcription, classifying people, and high-risk decision-making uses.41

Run and use notes

Documented facts only. No hardware or performance claims are made without a cited source and stated assumptions.
  • The Hugging Face card documents use through the Transformers speech-recognition pipeline, including chunked long-form transcription with 30-second chunks for large-v3; the openai-whisper package loads it by the name "large-v3".13

Organization context

Provenance and derivatives

Trained by OpenAI. Part of its training data was pseudo-labeled with OpenAI's earlier Whisper large-v2 model.31

Catalog records that name this entry in their provenance:

Other releases in the Whisper family

Whisper family overview

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: U.S. headquarters

The model was released by OpenAI in its openai/whisper repository and on its Hugging Face account. OpenAI Group PBC lists its address as 1455 3rd Street, San Francisco, California, in a February 2026 agreement filed with the SEC.4310

Assessed Sep 29, 2026

Sources

  1. 1.
    openai/whisper-large-v3 model card (external site: huggingface.co)

    OpenAI (Hugging Face) · Model card · accessed Sep 29, 2026

  2. 2.
    openai/whisper-large-v3 (Hugging Face model metadata) (external site: huggingface.co)

    OpenAI (Hugging Face) · Model card · accessed Sep 29, 2026

  3. 3.
    Whisper large-v3 (openai/whisper discussion #1762) (external site: github.com)

    OpenAI (GitHub) · Release notes · published Nov 6, 2023 · accessed Sep 29, 2026

  4. 4.
    Model Card: Whisper (external site: github.com)

    OpenAI (GitHub) · Model card · accessed Sep 29, 2026

  5. 5.
    openai/whisper README (external site: github.com)

    OpenAI (GitHub) · Repository · accessed Sep 29, 2026

  6. 6.
    openai/whisper LICENSE (external site: github.com)

    OpenAI (GitHub) · License · accessed Sep 29, 2026

  7. 7.
  8. 8.
  9. 9.
    Robust Speech Recognition via Large-Scale Weak Supervision (arXiv 2212.04356) (external site: arxiv.org)

    arXiv (OpenAI authors) · Paper · published Dec 6, 2022 · accessed Sep 29, 2026

  10. 10.
    Exhibit 10.1: Equity commitment letter agreement between OpenAI Group PBC and Amazon (external site: sec.gov)

    U.S. Securities and Exchange Commission (Amazon.com, Inc. filing) · Filing · published Feb 27, 2026 · accessed Sep 29, 2026

This listing is not an endorsement, a safety assessment, or a federal approval.

Support Us

Help keep USASI useful.

Optional. No USASI account required. Payment takes place on the linked provider’s website (Buy Me a Coffee).

About supporting this project