Titan AI LogoTitan AI

sherpa-onnx

8,669
955
C++

Project Description

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

sherpa-onnx: Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD

Project Title

sherpa-onnx — Next-gen Speech Processing with ONNX Runtime for Offline and Embedded Systems

Overview

Sherpa-onnx is an open-source project that enables advanced speech processing capabilities such as speech-to-text, text-to-speech, speaker diarization, and more, using ONNX Runtime. It is designed to work offline and is optimized for embedded systems, making it a unique solution for applications requiring local processing without internet connectivity.

Key Features

  • Supports a wide range of speech processing functions including ASR, TTS, speaker diarization, and VAD.
  • Works offline, suitable for environments without internet access.
  • Optimized for embedded systems like Android, iOS, HarmonyOS, Raspberry Pi, and RISC-V.

Use Cases

  • Developers creating voice-activated applications for smart devices that require offline functionality.
  • Enterprises implementing speech recognition systems in environments with limited or no internet access.
  • Researchers and developers in the field of speech technology needing a versatile tool for various speech processing tasks.

Advantages

  • Supports multiple programming languages, making it accessible to a broad developer community.
  • Works across various platforms and architectures, including x86, ARM, and RISC-V.
  • Offers a high degree of flexibility with support for both streaming and non-streaming speech recognition.

Limitations / Considerations

  • The project's license is currently unknown, which may affect its use in commercial applications.
  • As an open-source project, it relies on community support for updates and maintenance.
  • Performance may vary depending on the specific hardware and use case.

Similar / Related Projects

  • Kaldi: A well-known open-source speech recognition toolkit, but without the focus on ONNX Runtime and offline capabilities.
  • Mozilla DeepSpeech: An open-source speech-to-text engine that also supports offline use but is not as widely supported across different platforms and languages as sherpa-onnx.
  • ESPnet: A popular end-to-end speech processing toolkit that offers a range of functionalities but may not match sherpa-onnx in terms of platform support and offline capabilities.

Basic Information


📊 Project Information

  • Project Name: sherpa-onnx
  • GitHub URL: https://github.com/k2-fsa/sherpa-onnx
  • Programming Language: C++
  • ⭐ Stars: 7,727
  • 🍴 Forks: 898
  • 📅 Created: 2022-09-01
  • 🔄 Last Updated: 2025-10-11

🏷️ Project Topics

Topics: [, ", a, a, r, c, h, 6, 4, ", ,, , ", a, n, d, r, o, i, d, ", ,, , ", a, r, m, 3, 2, ", ,, , ", a, s, r, ", ,, , ", c, p, p, ", ,, , ", c, s, h, a, r, p, ", ,, , ", d, o, t, n, e, t, ", ,, , ", i, o, s, ", ,, , ", l, a, z, a, r, u, s, ", ,, , ", l, i, n, u, x, ", ,, , ", m, a, c, o, s, ", ,, , ", m, f, c, ", ,, , ", o, b, j, e, c, t, -, p, a, s, c, a, l, ", ,, , ", o, n, n, x, ", ,, , ", r, a, s, p, b, e, r, r, y, -, p, i, ", ,, , ", r, i, s, c, -, v, ", ,, , ", s, p, e, e, c, h, -, t, o, -, t, e, x, t, ", ,, , ", t, e, x, t, -, t, o, -, s, p, e, e, c, h, ", ,, , ", v, i, t, s, ", ,, , ", w, i, n, d, o, w, s, ", ]



This article is automatically generated by AI based on GitHub project information and README content analysis

Titan AI Explorehttps://www.titanaiexplore.com/projects/sherpa-onnx-531380835en-USTechnology

Project Information

Created on 9/1/2022
Updated on 10/31/2025