Model reference · open weights
midashenglm-gen is an open-weight audio or speech model from mispeech, 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
MiDashengLM-Gen [](https://arxiv.org/abs/2608.11804) [](https://huggingface.co/mispeech/midashenglm-gen) [](https://xingws.github.io/midashenglm-gen-demo/) [](https://github.com/xiaomi-research/midashenglm-gen) English | 中文 MiDashengLM-Gen is an end-to-end framework that uses a pre-trained Large Language Model and audio tokenizer as the backbone, combined with per-token conditional flow matching for autoregressive, variable-length mixed-audio scene generation. It generates coherent 16 kHz audio scenes that simultaneously blend speech, music, sound effects, and environmental acoustics from structured text descriptions. Architecture Left: training pipeline with flow matching loss. Right: autoregressive inference pipeline. Key components: Input Format Input uses structured multi-view captions with special tokens to describe different aspects of an audio scene. Use <|unknown| for absent elements. Installation Quick Start Batch Generation Generation Parameters Citation License Apache 2.0 Use Restrictions You are solely responsible for your use of MiDashengLM-Gen and any outputs, actions, or consequences arising therefrom, and you agree not to use MiDashengLM-Gen or any derivatives thereof: - For any unlawful, fraudulent, or malicious purpose, or in any manner that violates any applicable laws or regulations; - To infringe upon the intellectual property rights, privacy rights, publicity rights, or other lawful rights or interests of any third party; - To exploit, harm, harass, defame, unlawfully discriminate against, or otherwise adversely affect any individual or group, including minors or vulnerable persons; - For any military purpose or application.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | mispeech |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 2.9B |
| Variants | 1 |
| Runs with | transformers |
| Released | 2026-08-12 |
| Popularity | 1k downloads / month |
| Likes | 41 |
| 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 |
|---|---|---|---|---|---|
| midashenglm-gen | 2.9B | BF16 | ~6.6 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys midashenglm-gen for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (midashenglm-gen 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="midashenglm-gen" -F file=@audio.mp3
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗