aprilasr is a minimal library that provides an API for offline streaming speech-to-text applications
This library is currently under development. Some features are unimplemented, it may have bugs and crashes, and there may be significant changes to the API. It may not yet be production-ready.
Furthermore, there's only one model that only does English and has some accuracy issues at that.
The library has a C API, and there are C# and Python bindings available, but these may not be stable yet.
An example use of this library is provided in
example.cpp. It can perform speech recognition on a wave file, or do streaming recognition by reading stdin.
It's built as the target
main. After building aprilasr, you can run it like so:
$ ./main /path/to/file.wav /path/to/model.april
For streaming recognition, you can pipe parec into it:
$ parec --format=s16 --rate=16000 --channels=1 --latency-ms=100 | ./main - /path/to/model.april
To make your own models, check out
Building requires ONNXRuntime v1.13.1. You can either try to build it from source or just download the release binaries.
./download_onnx_linux_x64.sh for linux-x64.
For other platforms the script should be very similar, or visit https://github.com/microsoft/onnxruntime/releases/tag/v1.13.1 and download the right zip/tgz file for your platform and extract the contents to a directory named
You may also define the env variable
ONNX_ROOT containing a path to where you extracted the archive, if placing it in
lib isn't a choice.
You don't need to do this if you've downloaded ONNXRuntime.
Follow the instructions here: https://onnxruntime.ai/docs/how-to/build/inferencing.html#linux
cd build/Linux/RelWithDebInfo/ sudo make install
$ mkdir build $ cd build $ cmake -DCMAKE_BUILD_TYPE=Release .. $ make -j4
You should now have
main fails because it can't find
libonnxruntime.so.1.13.1, you may need to make
libonnxruntime.so.1.13.1 accessible like so:
$ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:`pwd`/../lib/lib/
Create a folder called
lib in the april-asr folder.
Download onnxruntime-win-x64-1.13.1.zip and extract the insides of the onnxruntime-win-x64-1.13.1 folder to the
Run cmake to configure and generate Visual Studio project files. Make sure you select x64 as the target if you have downloaded the x64 version of ONNXRuntime.
ALL_BUILD.vcxproj and everything should build. The output will be in the Release or Debug folders.
When running main.exe you may receive an error message like this:
The application was unable to start correctly (0xc000007b)
To fix this, you need to make onnxruntime.dll available. One way to do this is to copy onnxruntime.dll from lib/lib/onnxruntime.dll to build/Debug and build/Release. You may need to distribute the dll together with your application.
Currently I'm developing Live Captions, a Linux desktop app that provides live captioning.
Thanks to the k2-fsa/icefall contributors for creating the speech recognition recipes and models.
This project makes use of a few libraries:
- pocketfft, authored by Martin Reinecke, Copyright (C) 2008-2018 Max-Planck-Society, licensed under BSD-3-Clause
- Sonic library, authored by Bill Cox, Copyright (C) 2010 Bill Cox, licensed under Apache 2.0 license
- tinycthread, authored by Marcus Geelnard and Evan Nemerson, licensed under zlib/libpng license
The bindings are based on the Vosk API bindings, which is another speech recognition library based on previous-generation Kaldi. Vosk is Copyright 2019 Alpha Cephei Inc. and licensed under the Apache 2.0 license.