Open Source C++ Speech Recognition Software

whisper.cpp is a lightweight, C/C++ reimplementation of OpenAI’s Whisper automatic speech recognition (ASR) model—designed for efficient, standalone transcription without external dependencies. The entire high-level implementation of the model is contained in whisper.h and whisper.cpp. The rest of the code is part of the ggml machine learning library. The command downloads the base.en model converted to custom ggml format and runs the inference on all .wav samples in the folder samples. whisper.cpp supports integer quantization of the Whisper ggml models. Quantized models require less memory and disk space and depending on the hardware can be processed more efficiently.

Vosk is an offline open source speech recognition toolkit. It enables speech recognition for 20+ languages and dialects - English, Indian English, German, French, Spanish, Portuguese, Chinese, Russian, Turkish, Vietnamese, Italian, Dutch, Catalan, Arabic, Greek, Farsi, Filipino, Ukrainian, Kazakh, Swedish, Japanese, Esperanto, Hindi, Czech, Polish. More to come. Vosk models are small (50 Mb) but provide continuous large vocabulary transcription, zero-latency response with streaming API, reconfigurable vocabulary and speaker identification. Speech recognition bindings are implemented for various programming languages like Python, Java, Node.JS, C#, C++, Rust, Go and others. Vosk supplies speech recognition for chatbots, smart home appliances, and virtual assistants. It can also create subtitles for movies, and transcription for lectures and interviews. Vosk scales from small devices like Raspberry Pi or Android smartphones to big clusters.

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference. Boost deep learning performance in computer vision, automatic speech recognition, natural language processing and other common tasks. Use models trained with popular frameworks like TensorFlow, PyTorch and more. Reduce resource demands and efficiently deploy on a range of Intel® platforms from edge to cloud. This open-source version includes several components: namely Model Optimizer, OpenVINO™ Runtime, Post-Training Optimization Tool, as well as CPU, GPU, MYRIAD, multi device and heterogeneous plugins to accelerate deep learning inferencing on Intel® CPUs and Intel® Processor Graphics. It supports pre-trained models from the Open Model Zoo, along with 100+ open source and public models in popular formats such as TensorFlow, ONNX, PaddlePaddle, MXNet, Caffe, Kaldi.

Kaldi is an open source toolkit for speech recognition research. It provides a powerful framework for building state-of-the-art automatic speech recognition (ASR) systems, with support for deep neural networks, Gaussian mixture models, hidden Markov models, and other advanced techniques. The toolkit is widely used in both academia and industry due to its flexibility, extensibility, and strong community support. Kaldi is designed for researchers who need a highly customizable environment to experiment with new algorithms, as well as for practitioners who want robust, production-ready ASR pipelines. It includes extensive tools for data preparation, feature extraction, acoustic and language modeling, decoding, and evaluation. With its modular design, Kaldi allows users to adapt the system to a wide range of languages and domains. As one of the most influential projects in speech recognition, it has become a foundation for much of the modern work in ASR.

Speech recognition research toolkit

Flashlight is a fast, flexible machine learning library written entirely in C++ by Facebook AI Research and the creators of Torch, TensorFlow, Eigen, and Deep Speech. Native support in C++ and simple extensibility make Flashlight a powerful research framework that's hackable to its core and enables fast iteration on new experimental setups and algorithms with little unopinionated and without sacrificing performance. In a single repository, Flashlight provides apps for research across multiple domains. Flashlight can be broken down into several components as described above. Each component can be incrementally built by specifying the correct build options. Flashlight is most-easily built and installed with vcpkg. Both the CUDA and CPU backends are supported with vcpkg. For either backend, first, install Intel MKL. Flashlight app binaries are also built for the selected features and are installed into the vcpkg install tree's tools directory.

Software for speech recognition in English & Polish languages. Basic versions of SkryBot: 1. SkryBot Home Speech (English Language) - https://sourceforge.net/projects/skrybotdomowy/files/ReleasesEnglish/InstalatorSkryBotHomeSpeechDemo-2.6.9.18117.exe/download 2. SkryBot DoMowy (Polish Language) - https://sourceforge.net/projects/skrybotdomowy/files/ReleasesPolish/InstalatorSkryBotDoMowyDemo-2.4.9.18117.exe/download More help: https://sourceforge.net/p/skrybotdomowy/wiki/ Domain advanced versions (Polish Language) 1. SkryBot Prawo - for judicial professionals. 2. SkryBot Administracyjny - for civil and government administration. 3. SkryBot Medycyna Rodzinna - for physicians Professional version of SkryBot (commercial) offers you: 1. Audio conversion and cutting sound files into smaller ones. 2. Searching for words or phrases in sound files (recognized by SkryBot). 3. Editing sound files and automatic cutting off long silence parts in audio file.

Press and hold the hotkey, speak, and release — Aura instantly transcribes your speech and types the text right under your cursor in any Windows application. Runs 100% offline via local models (Whisper, NVIDIA Parakeet with CUDA GPU acceleration) or connects to cloud providers (Gemini, Groq, OpenAI, Hugging Face, Custom API). 100% Free & Open Source (AGPL-3.0) — no subscriptions, paywalls, telemetry, or advertisements.

A speech synthesis and recognition library that is cross-platform, accessible from Java and C++, and has a very small API. Uses CMU Sphinx4 and FreeTTS internally.

Voice XML Enabling Software (VXES) is an application that connects a VoiceXML Interpreter, a telephony platform, and MRCP servers that provide services for Automatic Speech Recognition and Text to Speech Synthesis. C++, Windows & Linux OS supported

Augmenting other natural interfaces namely handwriting, speech recognition to input Indian language characters to the computer. Speech synthesis is also provided to read out local language text.

Java library and tools to create open source speech recognition applications. Generates dialogs for conversational interfaces. Works with a popular open source speech recognition library.

CJ7 is an open-source speech recognition engine.

BTK contains C++ and Python libraries that implement speech processing and microphone array techniques such as speech feature extraction, speech enhancement, speaker tracking, beamforming, dereverberation and echo cancellation algorithms. The Millennium ASR provides C++ and python libraries for automatic speech recognition. The Millennium ASR implements a weighted finite state transducer (WFST) decoder, training and adaptation methods. These toolkits are meant for facilitating research and development of automatic distant speech recognition.

EBBA is a project aiming to develop an advanced chatbot by combining AIML, 3d facial expressions, speech synthesizer, speech recognition and an iq-test solving functionality.

Open source speech models for Julius speech decoder. Its aim is to give access a wider community of speech recognition enthusiasts to quality models, which they can use in their own projects on different OS platforms (Unix, Windows, etc...) All of the models are based on HTK modelling software and data sets available freely on the Internet.

The aim of this project is to develop a software to assist speech recognition systems users by displaying outputs of their systems.

Developpement of speech recognition software and libraries for the linux system. Should allow evryone to integrate speech recognition in his software very easily.

ROSA is an open source agent implementation. It will contain a speech engine, a speech recognition engine and many more...

Rodney is an upper torso humanoid robot with stereo vision, speech recognition and a wide variety of body and head movements. This project is designed to be an open source repository for the software which comprises its control system.

SpecimenPhoto controls a Canon Powershot camera for specimen archival photography. Each photograph is assigned a case number, labeled and stored. Identification is manual or "hands free" using separately available barcode and speech recognition modules.

World Voice Recognition est un programme OpenSource de reconnaissance vocal dont le but est de faire la liaison entre plusieurs modules crée par n'importe quelle developpeur ( Module du microphone, module de reconnaissance vocal, module pour faire parler l'ordinateur, ou des plugins : par exemple la météo ). La SDK est compatible avec n'importe quelle language de programmation (ASM,C++,Ada,Java...) sur toutes les platformes (Windows, Mac et Linux). Tous les developpeurs peuvent programme un module et le publier sur le site en s'inscrivant gratuitement. Les utilisateurs peuvent telecharger gratuitement ces modules sur le store.

First, install Flashlight (using the 0.3 branch is required) with the ASR application. This repository includes recipes to reproduce the following research papers as well as pre-trained models. All results reproduction must use Flashlight <= 0.3.2 for exact reproducibility. At least one of LZMA, BZip2, or Z is required for LM compression with KenLM. It is highly recommended to build KenLM with position-independent code (-fPIC) enabled, to enable python compatibility. After installing, run export KENLM_ROOT_DIR=... so that wav2letter++ can find it. This is needed because KenLM doesn't support a make install step.wav2letter++ expects audio and transcription data to be prepared in a specific format so that they can be read from the pipelines. Each dataset (test/valid/train) needs to be in a separate file with one sample per line. A sample is specified using 4 columns separated by space (or tabs).

Graphical User Interface and advanced facilities for training the speech recognition system Sphinx-III (using SphinxTrain).