RealSmile
Mini toolsMiMo V2.5 ASR
By Xiaomi
MiMo-V2.5-ASR is Xiaomi’s 8B automatic speech recognition model built for hard acoustic and linguistic settings. The model card says it handles Mandarin Chinese and English, multiple Chinese dialects including Wu, Cantonese, Hokkien, and Sichuanese, code-switched speech, lyrics, noisy environments, overlapping multi-party speech, and knowledge-dense content. Xiaomi describes it as achieving state-of-the-art results across a broad range of benchmarks and highlights strong English performance on challenging cases such as AMI
New
Multimodal
Gen 3
Overview
MiMo-V2.5-ASR is Xiaomi MiMo’s state-of-the-art end-to-end ASR model for robust transcription across Mandarin, English, Chinese dialects, code-switching, songs, noisy audio, and multi-speaker conversations. It is an 8B model aimed at difficult real-world recognition scenarios rather than only clean speech.
About Xiaomi
Consumer electronics and smart device company making smartphones, wearables, IoT products, home appliances, smart TVs, scooters, and connected lifestyle hardware.
View Company ProfileTools using MiMo V2.5 ASR
No tools found for this model yet.
Last updated: April 24, 2026
