OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Salmonn

Salmonn is a public research repository for a family of multimodal large language models, with releases addressing speech, audio processing, speech quality assessment and audio-visual understanding.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Salmonn — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use the repository when selecting a SALMONN-family research release for a speech, audio-processing or audio-visual task; check the corresponding branch for the materials relevant to that release.

Who it is for

  • Researchers exploring multimodal language models for speech or audio tasks.
  • Developers looking for research releases, checkpoints or training materials to build task-specific prototypes.

Documented uses

  • Explore model releases for speech and audio-related tasks.
  • Find an audio-visual model release for video understanding work.
  • Use released training code, annotations or checkpoints as a starting point for research.
Before you choose

Requirements & limits

The repository is public and specifies an Apache-2.0 license.

  • Releases have different tasks and materials; the repository points to separate branches and related projects.
  • The speech-quality release includes data-processing scripts and fine-tuned checkpoints, while other releases have their own materials.
  • The repository mentions inference and training code across releases, but does not provide one shared setup or inference workflow in the cited overview.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Choose a SALMONN research release to explore

Find the project branch or linked release corresponding to a SALMONN model variant or research task.

Before you start

  • Access to the SALMONN GitHub repository.

Steps

  1. Open the SALMONN repository and review the listed model-family releases.

  2. Select the linked branch or repository matching the intended variant, such as SALMONN, video-SALMONN, or speech-quality assessment.

  3. Follow that release's page for its own details.

Expected outcome

You reach the selected variant's project page for further information.

Guide limitations

  • The repository index does not provide setup or execution instructions for these variants; consult the selected release page.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
bytedance/SALMONN · Official homepage title · retained in its source language
How we review sourcesSuggest a correction