Awesome GitHub RepositoriesSpeech Recognition Engines

Azure Docs is the official technical documentation repository for Microsoft Azure, the cloud computing platform. It provides comprehensive guidance on the full spectrum of Azure services, covering everything from core infrastructure components like virtual machines, Kubernetes clusters, and serverless computing to platform services for AI, machine learning, data analytics, and storage. The documentation details how to provision, manage, and govern cloud resources at scale, including policy enforcement, identity management, and cost optimization. The documentation distinguishes Azure through i

Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox.

FunClip is an open-source tool that transcribes speech from video files and clips segments based on text, speaker, or AI analysis. It combines speech recognition with speaker diarization, audio event detection, and visual content understanding to identify and extract relevant portions of a video. The tool distinguishes itself through several integrated capabilities. It supports hotword-weighted speech recognition, which improves transcription accuracy for specific terms like names or jargon by boosting their probability during decoding. A large language model can interpret the transcribed tex

यह प्रोजेक्ट एक हार्डवेयर-त्वरित ट्रांसक्रिप्शन सर्वर और ऑफ़लाइन सबटाइटल जनरेटर है। यह एक स्पीच-टू-टेक्स्ट टूल के रूप में कार्य करता है जो Whisper मॉडल का उपयोग करके ऑडियो और वीडियो फाइलों को सादे टेक्स्ट, JSON और SRT सबटाइटल फॉर्मेट में बदलता है। यह सिस्टम एक OpenAI Audio API एमुलेटर के रूप में कार्य करता है, जो एक स्थानीय सर्वर प्रदान करता है जो एक विशिष्ट ऑडियो इंटरफ़ेस की नकल करता है। यह इसे क्लाइंट सॉफ्टवेयर में बदलाव की आवश्यकता के बिना मौजूदा क्लाइंट कॉन्फ़िगरेशन में ट्रांसक्रिप्शन प्रदान करने की अनुमति देता है। यह सेवा वॉयस रिकग्निशन गति बढ़ाने के लिए GPU त्वरण का उपयोग करती है और हार्डवेयर डिटेक्शन व संसाधन खपत अनुकूलन के लिए यूटिलिटी शामिल करती है। यह डेटा गोपनीयता के लिए ऑफ़लाइन मॉडल इन्फरेंस का सपोर्ट करती है और टेक्स्ट को सरलीकृत और पारंपरिक लिपियों के बीच बदलने के लिए पोस्ट-प्रोसेसिंग क्षमताएं प्रदान करती है।

Jasper Client एक वॉयस कंप्यूटिंग क्लाइंट और एक्सटेंसिबल स्पीच फ्रेमवर्क है जिसे प्राकृतिक भाषा के भाषण को हार्डवेयर क्रियाओं और सेवा अनुरोधों में अनुवादित करने के लिए डिज़ाइन किया गया है। यह एक वॉयस कमांड इंटरफेस के रूप में कार्य करता है जो ऑडियो कैप्चर, ट्रांसक्रिप्शन और क्रिया निष्पादन की एंड-टू-एंड प्रक्रिया का प्रबंधन करता है। यह सिस्टम एक मॉड्यूलर आर्किटेक्चर की सुविधा देता है जो कस्टम प्लगइन्स, विभिन्न स्पीच रिकग्निशन इंजन और सिंथेसिस प्रोवाइडर्स के एकीकरण की अनुमति देता है। यह प्लगइन-आधारित दृष्टिकोण मुख्य तर्क को बदले बिना नए वक्ताओं और क्षेत्रीय भाषा क्षमताओं को जोड़ने का समर्थन करता है। क्लाइंट में एक वेक-वर्ड डिटेक्शन इंजन शामिल है जो विशिष्ट ध्वनिक ट्रिगर्स के लिए बैकग्राउंड ऑडियो स्ट्रीम की निगरानी करता है। इंटरफेस रिस्पॉन्सिवनेस बनाए रखने के लिए, यह एक मल्टी-थ्रेडेड ऑडियो पाइपलाइन का उपयोग करता है जो ऑडियो प्रोसेसिंग और ट्रांसक्रिप्शन को अलग-अलग निष्पादन थ्रेड्स में ऑफलोड करता है।

CTranslate2 is a C++ inference engine and runtime for Transformer models, designed to execute models on both CPU and GPU with optimizations for speed and memory efficiency. It functions as a model format converter, quantization tool, and REST API server, enabling deployment of neural machine translation, automatic speech recognition, and text generation models. The engine distinguishes itself through a suite of runtime optimizations including layer fusion, weight-matrix quantization, batch-by-length grouping, and a caching allocator that reuses GPU memory. It supports tensor-parallel model di

PocketSphinx is an offline speech recognition engine that converts raw audio from files or live microphone streams into written text without requiring a network connection. It functions as a speech-to-text library, a real-time transcription engine, and a voice command processor, capable of detecting and transcribing spoken commands from continuous audio streams with configurable acoustic and language models. The engine uses weighted finite-state transducers to represent acoustic, phonetic, and language models as a single search graph for efficient decoding. It employs fixed-point acoustic mod

This project is a deep learning framework designed for end-to-end speech-to-text transcription. It utilizes the WaveNet neural network architecture to process spoken audio input and generate written text transcripts, leveraging connectionist temporal classification to map variable-length audio sequences to character-level outputs. The system distinguishes itself through a comprehensive training pipeline that supports distributed execution across multiple graphics processing units. It includes specialized utilities for audio data augmentation and the transformation of raw audio files into opti

Whisper streaming is an automated speech recognition engine designed to convert live audio into text. It functions as a network-based transcription server that accepts raw audio data from remote clients and returns incremental text results in real-time. The system distinguishes itself through its ability to process audio streams incrementally, allowing for immediate transcription and translation as speech is captured. It incorporates voice activity detection to isolate human speech from background noise and utilizes sliding-window buffering to manage incoming audio segments, ensuring that pro

Whisper Real-Time is a speech-to-text engine designed to convert continuous microphone input into written transcripts. It functions as a real-time audio processor that leverages the OpenAI Whisper model to generate immediate textual output from live spoken language. The system utilizes a transformer-based architecture to map audio sequences to text tokens. It manages incoming data through a sliding-window buffering mechanism and a circular buffer, which ensures a steady stream of audio for the inference engine. To maintain accuracy during continuous processing, the software employs a stateful

Whishper is a graphical user interface for transcribing audio and video files into text using the Whisper model. It serves as a speech-to-text tool and subtitle file generator that converts spoken content into editable text and timed subtitle formats. The project features an integrated transcription and translation interface, allowing users to refine automated results and convert transcribed text into different languages. It includes a visual editor for correcting speech recognition errors, adjusting segment timecodes, and performing bilingual translation reviews. The system handles the full

This project is a machine learning toolkit designed for the development, training, and deployment of automatic speech recognition engines. It provides a comprehensive framework for converting spoken audio into written text, specifically supporting models trained on Mandarin and English datasets. The library utilizes an end-to-end neural architecture that processes raw audio input directly into character sequences, bypassing the need for intermediate linguistic alignment. It incorporates signal processing techniques to transform sound waves into numerical spectrograms and feature vectors, whic

Julius is a high-performance, open-source speech recognition engine designed for large vocabulary continuous speech recognition. It functions as a comprehensive framework utilizing Hidden Markov Model-based acoustic modeling and N-gram language models to convert live or recorded audio into text. The engine is built to support real-time streaming and provides a network-accessible service that allows external applications to manage recognition sessions and receive transcription results through programmatic commands. The engine distinguishes itself through its modular architecture and support fo

This project is a terminal-based optical character recognition engine that uses neural network models to extract text and spatial layout data from images. It functions as both a command-line utility for automated text processing and a library for integrating machine learning-powered recognition into broader workflows. The engine distinguishes itself through a modular processing pipeline that supports custom model loading and memory-mapped weight initialization for efficient execution. It preserves document structure by tracking precise geometric coordinates for every detected text element, an

Expo Speech Recognition is a cross-platform mobile module that converts live microphone audio and pre-recorded files into text using native speech engines. It provides offline speech recognition capabilities by downloading and verifying local speech models to enable on-device processing without an active network connection. The library includes session lifecycle management to start, stop, or abort recording, alongside real-time spoken language detection with confidence scoring. It emits volume change events for metering interfaces, handles audio session configuration and routing, and persist