MOSS-Transcribe: a 0.9B open model that labels who said what

MOSS-Transcribe: a 0.9B open model that labels who said what

1 month ago

@ai-ml-today Subscribe

A point-nine-billion-parameter open model takes long, multi-speaker audio and returns a transcript that already knows who said what. That's MOSS-Transcribe-Diarize, and it does the whole thing in a single pass.

Ask

Ask about this presentation

Answers are generated from this presentation.

Chapters

Up next

Autoplay

Apodex 1.1 mini · the same file, run alone and run as a team

@ai-ml-today · 16 hours ago

Ornith-1.5 · an open model trained on problems it wrote for itself

@ai-ml-today · 3 days ago

MOSS-VL · an open 11B video model trained to decide, after every frame, whether to speak or stay silent

@ai-ml-today · 5 days ago

Qwen3.8-27B · a 27B open model anyone can download averages 84.3 across real desktop jobs on Qwen’s own run, and loses the widest row on its own card by nine points

@ai-ml-today · 1 week ago

MiLMMT-46-v1.0 · Xiaomi finished training an open translator on sentences that had no translation attached, and the scores it now leads on are produced by the two models that graded it

@ai-ml-today · 1 week ago

BDH-CQ — a 150M-parameter system that learns a puzzle rule from the worked examples in front of it and does its thinking as numbers, never as words

@ai-ml-today · 2 weeks ago

Muse Glimmer 30B, Meta’s open agent model, and the second tiny model that guesses sixteen words ahead so it runs fast on one consumer graphics card

@ai-ml-today · 2 weeks ago

JoyAI-Video-Edit, JD’s open 16B model that edits a video while the video is still playing, at about 30 frames a second on one Nvidia B200

@ai-ml-today · 2 weeks ago

Inkling-Small, Thinking Machines’ 12B-active / 276B open mixture-of-experts model that out-reasons its own 3.5× bigger flagship

@ai-ml-today · 2 weeks ago

Maple-Preview, DeepGrove’s 20-billion-parameter ternary reasoning model that runs on a Mac mini

@ai-ml-today · 2 weeks ago

Hunyuan3D-Buffalo, Tencent’s one model that builds, understands, and edits 3D from words

@ai-ml-today · 2 weeks ago

MiniMax H3, an open model that makes a video and its soundtrack in one pass

@ai-ml-today · 2 weeks ago