Ming-3.0-asr-tiny

Released
2026-10-19
Last refreshed
2026-10-20
Status
Researched 1d ago
Open sourceCommercial use: permitted

Ming-3.0-asr-tiny is available now for general LLM work with open-source; evaluate it while provider pricing coverage matures.

InclusionAI releases · 18 in the last 12 months · this family litChangelog →
Specifications
Family
Ming 3.0
Released
2026-10-19
Parameters
8.6B (2B activated)
Architecture
Mixture of Experts
Specialization
speech-recognition
Openness
Open source
License
MITOSI-approvedPermitted
Weights
Available
Code
Unknown
Created by

InclusionAI is Ant Group's artificial general intelligence research lab, responsible for developing the Ling series of l

Hangzhou, China
Founded 2023
Website
Pricing

No tracked provider pricing is available yet.

About

Ming-3.0-asr-tiny is inclusionAI's speech recognition model from the Ming-3.0 release, combining the Ling-tiny-v3 language backbone with an audio encoder. It transcribes single-turn Chinese and English speech, covers regional dialects (evaluated on 15 dialect test sets including Cantonese, Minnan and Shanghainese), and can use hotwords or preceding dialogue to improve recognition of domain terms. Open weights under the MIT License.

Providers

No active provider routes are tracked for this model yet.

Capabilities

Audio

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

inclusionAI/Ming-3.0-asr-tiny