speech-to-speech

paper ,  speech-to-text ,  speech-to-speech ,  test-time-compute ,  test-time-scaling ,  rl-with-verifiable-rewards ,  step-audio ,  stepfun ,  mgrd ,  inverted-scaling ,  stepfun-audio ,  format-reward ,  self-cognition-error ,  textual-surrogate-reasoning ,  audio-llm

meta ,  multimodal ,  mms ,  asr ,  meta-ai ,  speech-to-text ,  seamlessm4t ,  translation ,  sonar ,  speech-to-speech ,  stopes ,  fairseq2 ,  speechmatrix ,  seamlessalign ,  nllb