Ming-3.0-asr-tiny
Ming-3.0-asr-tiny is a speech-recognition model for transcribing Chinese and English, including regional dialects. It supports context prompts with hotwords or preceding dialogue and is released with model weights, a tokenizer, custom Transformers code, and a runnable inference example.
What it does
Use it to transcribe speech locally or serve transcription through an OpenAI-compatible audio endpoint, with topic or hotword context to guide recognition.
- Availability
- Download the complete checkpoint from Hugging Face; runnable inference instructions are provided.
- Pricing model
- Not established
- Deployment
- Local inference on Linux with a compatible CUDA GPU; SGLang-Omni serving is documented.
- Privacy
- Not established
- Licence
- MIT License for model weights and original project code; bundled Apache-2.0 source files retain their own licenses.
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
6 claims- The model transcribes Chinese and English speech and covers regional dialects. [1]
It transcribes single-turn Chinese and English speech, covers regional dialects, and can use hotwords or preceding dialogue to improve recognition of domain-specific terms.
inclusionAI. Quoted text is outside CC BY 4.0 and keeps its original rights. - It accepts hotwords or dialogue context as part of the transcription prompt. [1]
- **Context ASR:** accepts relevant hotwords or dialogue context as part of the transcription prompt.
inclusionAI. Quoted text is outside CC BY 4.0 and keeps its original rights. - The repository includes model weights, a tokenizer, custom Transformers implementation, and runnable inference examples. [1]
This repository includes the model weights, tokenizer, custom Transformers implementation, and runnable inference example.
inclusionAI. Quoted text is outside CC BY 4.0 and keeps its original rights. - The documented local inference setup uses Python 3.12 on Linux with a compatible CUDA GPU. [1]
Use Python 3.12 on a Linux machine with a compatible CUDA GPU.
inclusionAI. Quoted text is outside CC BY 4.0 and keeps its original rights. - The documented output is transcription text without word-level timestamps or speaker diarization. [1]
- Output is transcription text, without word-level timestamps or speaker diarization.
inclusionAI. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model weights and original project code are released under the MIT License. [1]
The model weights and original project code are released under the [MIT License](./LICENSE), following the [Ming project](https://github.com/inclusionAI/Ming).
inclusionAI. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
inclusionAIOwner-controlled
https://huggingface.co/inclusionAI/Ming-3.0-asr-tiny
Retrieved 2026-10-28 00:51 UTC
Verified
Versions
2| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 2 | 2026-10-22 04:27 UTC | material change | access, pricing, availability, deployment | Current |
| 1 | 2026-10-21 05:23 UTC | publication | None | Current |
In briefs
2- A toolkit for voice agents that listen, respond, and take action Weekly brief 2026-W43
- Two Fibo models offer image generation and more targeted edits Daily brief 2026-10-21
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.