Speech and audio·EASYHUB JOURNAL
MiMo-Audio opens research into end-to-end speech pretraining
What changed
Xiaomi shares speech-model and encoding components to study few-shot task generalization from audio pretraining. Tokenizers and complete speech systems are different components, so their parameter counts must be identified separately.
- Original title
- 小米开源首个原生端到端语音大模型 Xiaomi-MiMo-Audio，对话自然度、交互适配达拟人化水准
- Source
- IT之家 · www.ithome.com
- Topic
- Speech and audio
- Source month
- 2025-09
This is a concise EasyHub summary of the linked source, not the full report or original reporting. Availability and preview conditions are described in the summary and original.
Summary page published · Editorial information