Baichuan Audio
Baichuan-Audio is an end-to-end speech interaction model that unifies audio understanding and audio generation for real-time bilingual dialogue
- Type
- Multimodal
- Weights
- Open
- Downloads
- 6
- License
- apache-2.0
- Library
- vokra
Model hub
vokra/baichuan-audio
- Repo
- vokra/baichuan-audio
- Access
- Public
Technical tags and languages
More from Baichuan Intelligent Technology
8
-
Baichuan 13B
Text
Baichuan-13B is a bilingual Chinese-English 13B-parameter model released in Base (pretrained) and Chat (align…
-
Baichuan 2
Text
Baichuan 2 is a next-generation open model series (7B and 13B) trained for stronger multilingual general and…
-
25k DL
Baichuan 7B
Text
Baichuan-7B is a bilingual Chinese-English 7B-parameter pretrained language model built for general text gene…
-
614 DL
Baichuan M1 14B
Multimodal
Baichuan-M1-14B is a medical-optimized 14B language model trained from scratch for strong clinical and genera…
-
499 DL
Baichuan M3 235B
Text
Baichuan-M3-235B is a medical-enhanced large language model trained to model clinical inquiry and decision-ma…
About Baichuan Intelligent Technology
1