Multimodal model

Raon-Speech

Raon-Speech is KRAFTON’s open-source 9B bilingual speech language model for English and Korean. It is built as a unified speech AI system that supports speech-to-text, text-to-speech, spoken QA, speech chat, and text QA, with low-latency generation and optional speaker-conditioned TTS.

KRAFTON Multimodal Closed cc-by-nc-4.0
Type
Multimodal
Weights
Closed
Downloads
3.4k
Likes
57
Pipeline
any to any
License
cc-by-nc-4.0

Model hub

KRAFTON/Raon-Speech-9B

Repo
KRAFTON/Raon-Speech-9B
Library
transformers
Access
Public
Technical tags and languages
en ko transformers safetensors raon feature-extraction speech audio multimodal any-to-any custom_code
Open on Hugging Face

Papers

1

More from KRAFTON

3

About KRAFTON

1

Video game company best known for PUBG: Battlegrounds, developing and publishing PC, console, and mobile games through studios worldwide.