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.
1 stories, newest first · one card per story
Kraken speech-to-speech translation model builds on Qwen3-8B with low-bitrate vector quantization and source-conditioned vocoding.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views