First open Basque speech language model built on LLaMA-Omni
Fine-tuning a Latxa backbone on translated, synthesized VoiceAssistant-400K data scored 3.86/5 content quality and 9.94% WER.
Stories per day · 30 days
3 RSS
2 stories, newest first · one card per story
Stories tagged #speech-language-model
Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning
Kraken speech-to-speech translation model builds on Qwen3-8B with low-bitrate vector quantization and source-conditioned vocoding.