MiDashengLM-Gen — MAESTRO mirror
Mirror of mispeech/midashenglm-gen (Xiaomi MiLM Plus, Apache-2.0, arXiv:2608.11804) maintained by AEmotionStudio for download-on-demand use inside MAESTRO.
MiDashengLM-Gen generates blended 16 kHz mono audio scenes — speech, music,
sound effects and ambience in one pass — from a structured multi-view caption
(<|caption|> <|asr|> <|speech|> <|sfx|> <|music|> <|env|>), 1–20 s,
via Qwen3-1.7B + per-token conditional flow matching + a Vocos vocoder.
Differences from upstream
- Precision: weights may be cast fp32 → bf16 (one
model.safetensors);NOTICErecords the payload precision and per-file sha256 digests. Upstream fp32 was sha256-verified against the hub before casting, and a bf16 payload is published only after an A/B parity pass on GPU. - Bundled tokenizer:
tokenizer/carries the Qwen3-1.7B tokenizer + config pinned at the revision recorded intokenizer/tokens_added.json(upstream fetches it from the network, unpinned, at construction time).tokens_added.jsonalso records the 28 special tokens appended in training order — loader drift fails loudly instead of generating noise. - No remote code: the
modeling_*.pytrust-remote-code files are not mirrored; MAESTRO vendors the inference code (Apache-2.0) in-tree.
License
Apache-2.0 (see LICENSE). Weights © 2026 MiLM Plus Xiaomi Inc.;
tokenizer files © Alibaba (Qwen), Apache-2.0. See upstream for the model
card, evaluation results and use-restriction notes.