https://github.com/k2-fsa/sherpa

Speech-to-text server framework with next-gen Kaldi
https://github.com/k2-fsa/sherpa

asr cpp ctc end-to-end-asr python pytorch speech-recognition transducer websocket

Last synced: 3 days ago
JSON representation

Speech-to-text server framework with next-gen Kaldi

• Host: GitHub
• URL: https://github.com/k2-fsa/sherpa
• Owner: k2-fsa
• License: apache-2.0
• Created: 2022-05-20T04:30:44.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2024-12-13T09:17:07.000Z (12 days ago)
• Last Synced: 2024-12-18T00:42:57.854Z (7 days ago)
• Topics: asr, cpp, ctc, end-to-end-asr, python, pytorch, speech-recognition, transducer, websocket
• Language: C++
• Homepage: https://k2-fsa.github.io/sherpa
• Size: 88.6 MB
• Stars: 573
• Watchers: 29
• Forks: 110
• Open Issues: 87
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# sherpa

`sherpa` is an open-source speech-text-text inference framework using

PyTorch, focusing **exclusively** on end-to-end (E2E) models,

namely transducer- and CTC-based models. It provides both C++ and Python APIs.

This project focuses on deployment, i.e., using pre-trained models to

transcribe speech. If you are interested in how to train or fine-tune your own

models, please refer to [icefall][icefall].

We also have other **similar** projects that don't depend on PyTorch:

  - [sherpa-onnx][sherpa-onnx]

  - [sherpa-ncnn][sherpa-ncnn]

> `sherpa-onnx` and `sherpa-ncnn` also support iOS, Android and embedded systems.

## Installation and Usage

Please refer to the **documentation** at 

## Try it in your browser

Try `sherpa` from within your browser without installing anything:

[icefall]: https://github.com/k2-fsa/icefall

[sherpa-onnx]: https://github.com/k2-fsa/sherpa-onnx

[sherpa-ncnn]: https://github.com/k2-fsa/sherpa-ncnn