A model series capable of outputting both speech and text. Despite its name, it is based on the Qwen2.5 series.
Specs
Params0.5B
LicenseNon-commercial
Tags
modelsmodels/llmsmodels/llms/multi-modalmodels/audio-generationartifacts/10
Related Models
A model series capable of outputting both speech and text. Despite its name, it is based on the Qwen2.5 series.
