Xiaomi MiMo-V2.5-ASR

Model overview

Xiaomi MiMo-V2.5-ASR speech recognition model.

audiospeechtranscriptionspeech to texttranscriptionlocal inferenceevaluation

Representative version

Company	Xiaomi
Release	2026-06-02
Release type	Model release
Parameters	8B
Architecture	MoE or sparse architecture; exact architecture not separately normalized.
Context	Not disclosed
Input modalities	audio
Output modalities	text
Tool use / function calling	Not disclosed
Structured output / reasoning	Not disclosed
Vision / audio / video	Confirmed: Audio
Open weights / License	Weights available / MIT License sourcexiaomi-mimo-v2-5-asr-phase-3-5 · 2026-07-15
Vendor API	Available Xiaomi MiMo-V2.5-ASR Hugging Face model cardxiaomi-mimo-v2-5-asr-phase-3-5 · 2026-06-02
OpenRouter	Not separately listed on OpenRouter
Pricing	No reliable public source
Benchmark	No reliable public source
Public signals	1 activity snapshot
Use cases	transcription / local inference / research evaluation / audio and speech
Claim evidence	Release / model specs / weightsXiaomi MiMo-V2.5-ASR Hugging Face model cardXiaomi MiMo-V2.5-ASR · 2026-06-02

OpenRouter

Pricing / context / availability

OpenRouter	Not separately listed on OpenRouter
OpenRouter listing	Not separately listed in the current OpenRouter public list
Mapped version	Xiaomi MiMo-V2.5-ASR xiaomi-mimo-v2-5-asr-phase-3-5
Pricing	No reliable public source
Context	Not disclosed
Speed/Latency	No reliable public source
Snapshot time	2026-07-15T20:11:41.551Z
Source	View source

Public activity counters

Platform	Entry	Downloads	Likes	Spaces	Time	Source
huggingface	XiaomiMiMo/MiMo-V2.5-ASR	2,733	101	1	2026-07-15T20:11:41.551Z	View source

Evidence gaps

OpenRouter not separately verifiedNo reliable benchmark sourceNo linkable real reviewSpeed/latency not disclosed