Skip to content

@AmphionTeam Amphion Team

Change the repository type filter

All

    Repositories list

    9 repositories

    • FlexiCodec

      Public
      [ICLR2026] FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates
      text-to-speechspeechamphion
      text-to-speechspeechamphionneural-audio-codec
      Python
      •
      MIT License
      •5•45•1•0•Updated Apr 13, 2026Apr 13, 2026

    • VoxSafeBench

      Public
      Python
      •
      Apache License 2.0
      •0•2•0•0•Updated Apr 1, 2026Apr 1, 2026

    • VoxSafeBench_demopage

      Public
      Python
      •0•0•0•0•Updated Apr 1, 2026Apr 1, 2026

    • TaDiCodec

      Public
      This repository contains a series of works on diffusion-based speech tokenizers, including the official implementation of the paper: "TaDiCodec: Text-aware Diff…
      Python
      •3•77•3•0•Updated Jan 25, 2026Jan 25, 2026

    • SpeechJudge

      Public
      SpeechJudge: Towards Human-Level Judgment for Speech Naturalness (https://arxiv.org/abs/2511.07931)
      Python
      •4•71•3•0•Updated Dec 23, 2025Dec 23, 2025

    • AnyAccomp

      Public
      AnyAccomp: Generalizable accompaniment generation for vocals and solo instruments, powered by a quantized melodic bottleneck.
      Python
      •
      MIT License
      •2•36•3•0•Updated Dec 22, 2025Dec 22, 2025

    • SA-Eval

      Public
      0•8•0•0•Updated Mar 20, 2025Mar 20, 2025

    • debatts

      Public
      HTML
      •1•5•0•0•Updated Dec 23, 2024Dec 23, 2024

    • SD-Eval

      Public
      [NeurIPS 2024] SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
      Python
      •
      Apache License 2.0
      •2•56•1•0•Updated Jun 25, 2024Jun 25, 2024
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.