MiMo-V2.5-ASR is an open-source automatic speech recognition model hosted on Hugging Face. It enables developers and researchers to transcribe audio to text using pre-trained weights, accessible via API or CLI. The model is suitable for building speech-enabled applications or conducting ASR research.
In the Speech to text space, MiMo V2.5 ASR takes a focused approach. It focuses on transcribing spoken audio into text using an open-source ASR model. MiMo V2.5 ASR is an open-source project aimed at developers and researchers working with speech recognition. MiMo V2.5 ASR is open source under the Apache-2.0 license. It ships for the web, the command line, and API, and it can be self-hosted.
It is developed by XiaomiMiMo, and it first shipped in 2026. Development happens publicly on GitHub with 281 stars and 8 commits in the last 90 days. Key capabilities include speech recognition, ASR model, and open weights.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do