Xiaomi releases MiMo-V2.5-ASR: open-source 8B speech recognition model supporting Mandarin, English, dialects, and song lyrics
By
Rohan Chaubey
Hard to chew. Probably not worth the jaw work.
Summary
MiMo-V2.5-ASR is an 8-billion-parameter open-source speech recognition model developed by Xiaomi. It supports transcription of Mandarin, English, eight Chinese dialects, code-switched speech, and song lyrics. The model is designed for ML engineers, researchers, and developers building real-world voice applications.
Key quotes
· 2 pulledMiMo-V2.5-ASR is an 8B open-source speech recognition model from Xiaomi that transcribes Mandarin, English, eight Chinese dialects, code-switched speech, and song lyrics.
Built for ML engineers, researchers, and developers building real-world voice applications.
You might also wanna read
Microsoft Open-Sources VibeVoice: A Speech-to-Text AI for Long-Form Audio Transcription
Microsoft has open-sourced VibeVoice, a frontier voice AI system that includes VibeVoice-ASR, a unified speech-to-text model capable of hand
GitHub·1mo ago
Xiaomi's MiMo-V2.5-Pro AI Model Achieves Perfect Score on University Compiler Project in 4.3 Hours
Xiaomi's MiMo-V2.5-Pro AI model achieved a perfect score (233/233) on Peking University's SysY compiler project — a complex Rust-based compi
Firethering·1mo ago
Meta Launches Omnilingual ASR Supporting Over 1,600 Languages
Meta introduces Omnilingual Automatic Speech Recognition (ASR), a suite of models that provides speech recognition capabilities for over 1,6
ai.meta.com·6mo ago
Developer Creates 9M-Parameter On-Device Model for Mandarin Pronunciation Feedback
A developer created a 9M-parameter CTC model trained on ~300 hours of transcribed Mandarin speech to grade pronunciation and tones. The tool
Xiaomi Launches MiMo API Open Platform Token Plan Globally, Announces Pricing Overhaul
Xiaomi announces the global launch of the MiMo API Open Platform Token Plan, along with a price adjustment for the MiMo-V2.5 series and the
platform.xiaomimimo.com·5d ago
Moonshine Voice: Open-Source On-Device Speech Recognition Toolkit for Edge Applications
Moonshine Voice is an open-source AI toolkit for developers building real-time voice applications that runs entirely on-device, offering fas
github.com·3mo ago