#model #output #api #bindings #version #deepspeech #deep-speech

deprecated sys deepspeech-sys

Bindgen output for the DeepSpeech C++ API

13 releases (7 breaking)

Uses old Rust 2015

0.9.1 Mar 5, 2022
0.9.0 Nov 14, 2020
0.8.0 Jul 30, 2020
0.6.1 Feb 1, 2020
0.0.1 Nov 26, 2017

#479 in #output

39 downloads per month
Used in deepspeech

MPL-2.0 license

22KB
103 lines

DEPRECATION NOTICE

This project is deprecated in favour of coqui-stt. Please use that project instead.

deepspeech-rs

docs crates.io

Rust bindings of Mozilla's DeepSpeech library.

The library is open source and performs Speech-To-Text completely offline. They provide pretrained models for English.

Quickstart

Preparation:

  1. Obtain the Deepspeech native_client library. The release announcement contains precompiled libraries for various targets.
  2. Download the pretrained models named like deepspeech-{version}-models.tar.gz from the release announcement and extract the zip file to some location.
  3. Add the directory where the native_client library lies to your LD_LIBRARY_PATH and LIBRARY_PATH environment variables.

You can now invoke the example via:

cargo run --release --example client <path-to-model-dir> <path-to-audio-file>

It will print out the recognized sequence on stdout. The format of the audio files is important: only mono files are supported for now.

All codecs that the awesome audrey library supports are supported.

See DeepSpeech's release announcement for more.

Supported versions of DeepSpeech

We currently support version 0.9.0 of the DeepSpeech library. We will always try to provide compatibility with the most recent release possible.

License

Licensed under Apache 2 or MIT (at your option). For details, see the LICENSE file.

All examples inside the examples/ folder are licensed under the CC-0 license.

The generated bindings (sys subdirectory in git, -sys crate on crates.io) fall under the Mozilla Public License, version 2.0.

License of your contributions

Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in the work by you, as defined in the Apache-2.0 license, shall be dual licensed / CC-0 licensed as above, without any additional terms or conditions.

No runtime deps