Skip to content

@kyutai-labs kyutai

Change the repository type filter

All

    Repositories list

    8 repositories

    • moshi

      Public
      Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
      Python
      •
      Apache License 2.0
      •603•7.5k•33•6•Updated Feb 22, 2025Feb 22, 2025

    • moshi-swift

      Public
      Swift
      •
      MIT License
      •5•73•1•4•Updated Feb 20, 2025Feb 20, 2025

    • hibiki

      Public
      Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- Hibiki adapts its flow to accumulate just enough context to produce a correct translation in real-time, chunk by chunk.
      Rust
      •
      Apache License 2.0
      •60•791•6•1•Updated Feb 9, 2025Feb 9, 2025

    • jax-flash-attn2

      Public
      JAX bindings for the flash-attention2 kernels
      C++
      •0•7•0•0•Updated Jan 16, 2025Jan 16, 2025

    • sphn

      Public
      python bindings for symphonia/opus - read various audio formats from python and write opus files
      Rust
      •
      Apache License 2.0
      •4•30•4•0•Updated Dec 22, 2024Dec 22, 2024

    • yomikomi

      Public
      A small rust-based data loader
      Rust
      •
      Apache License 2.0
      •0•22•0•0•Updated Dec 10, 2024Dec 10, 2024

    • ogg-table

      Public
      Ogg-vorbis reader with fast random access
      Rust
      •
      Other
      •1•6•0•0•Updated Aug 29, 2024Aug 29, 2024

    • jax-flash-attn3

      Public
      JAX bindings for the flash-attention3 kernels
      C++
      •1•11•0•0•Updated Aug 6, 2024Aug 6, 2024