Xiaomi · Speech-to-Text
MiMo V2.5 ASR
8B parameter end-to-end speech recognition model handling Mandarin dialects (Wu, Cantonese, Hokkien, Sichuanese), Chinese-English code-switching, song lyrics, and noisy multi-speaker audio — MIT licensed.
Open the source ↗Similar Audio & Speech releases
- NVIDIA Nemotron 3.5 Transcribe 30B-A4B
NVIDIA · Open multilingual ASR · Week 45, 2026
- Hy-SimulMT
Tencent Hunyuan · Simultaneous speech translation · Week 45, 2026
- Underdog Bark 3.0
Underdog · Speech Recognition · Week 44, 2026
- FluidVoice 1.6.11
altic-dev · Local Dictation App · Week 43, 2026
- Phonon-2
Fermion Research · Compressed English ASR · Week 41, 2026
- Whistle
Cactus Compute · Tiny On-Device ASR · Week 41, 2026
More from Xiaomi
- MiMo-V2.6-Pro / Flash
Xiaomi · Open-Weight MoE Models · Week 40, 2026
- MiDashengLM-Gen
Xiaomi · Audio Processing · Week 33, 2026
- MiMo-V2.5-Pro
Xiaomi · Code Generation · Week 17, 2026
- MiMo-V2-Omni
Xiaomi · Reasoning · Week 12, 2026
- MiMo-V2-Pro
Xiaomi · MoE Architecture · Week 12, 2026
- MiMo V2 Flash
Xiaomi · Text-to-Video · Week 51, 2025
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.