awesome-repositories.com
Blog
MCP
awesome-repositories.com

Découvrez les meilleurs dépôts open-source grâce à notre recherche par IA.

ExplorerRecherches sélectionnéesAlternatives open sourceLogiciels auto-hébergésBlogPlan du site
ProjetServeur MCPÀ proposNotre méthodologiePresse
Mentions légalesConfidentialitéConditions d'utilisation
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
davabase avatar

davabase/whisper_real_time

0
View on GitHub↗
2,938 stars·478 forks·Python·9 vues

Whisper Real Time

Whisper Real-Time est un moteur de synthèse parole-texte conçu pour convertir l'entrée microphone continue en transcriptions écrites. Il fonctionne comme un processeur audio en temps réel qui tire parti du modèle OpenAI Whisper pour générer une sortie textuelle immédiate à partir de la langue parlée en direct.

Le système utilise une architecture basée sur transformer pour mapper les séquences audio vers des jetons de texte. Il gère les données entrantes via un mécanisme de mise en mémoire tampon à fenêtre glissante et un tampon circulaire, qui assure un flux constant d'audio pour le moteur d'inférence. Pour maintenir la précision pendant le traitement continu, le logiciel emploie un contexte de transcription avec état qui conserve un historique des segments audio précédents.

Cet outil prend en charge une variété d'applications, incluant la transcription de parole en direct, l'automatisation des notes de réunion, le sous-titrage vocal en temps réel et le traitement des commandes vocales. L'implémentation utilise un pipeline d'inférence asynchrone pour découpler la capture audio du traitement du modèle, empêchant la boucle d'exécution principale de se bloquer pendant la transcription.

Features

  • Whisper-Based Engines - Provides a real-time transcription tool leveraging the transformer-based model for continuous audio processing.
  • Speech Recognition Engines - Utilizes a transformer-based speech recognition engine to map audio sequences directly to text tokens.
  • Real-Time Audio Transcribers - Converts continuous microphone input into written text in real time as the user speaks.
  • Speech-to-Text Engines - Acts as a speech-to-text engine that translates spoken language into written transcripts using deep learning models.
  • Speech Transcription Engines - Provides live speech transcription by converting continuous microphone input into written text using deep learning models.
  • Rolling Context Windows - Maintains a rolling history of previous audio segments to provide linguistic context for accurate real-time decoding.
  • Asynchronous Inference - Implements an asynchronous inference pipeline to decouple audio capture from model processing, preventing main-thread blocking.
  • Meeting Automation & Transcription - Automates meeting note generation by transcribing live discussions into searchable text documents.
  • Audio Stream Segmenters - Segments continuous microphone input into fixed-duration chunks using sliding-window buffering to maintain a steady stream for inference.
  • Real-Time Video Captioning - Generates instant text overlays for live audio streams to improve accessibility and provide immediate written records.
  • Voice Command Recognition - Captures live spoken input to trigger automated actions or control software interfaces through natural language recognition.

Historique des stars

Graphique de l'historique des stars pour davabase/whisper_real_timeGraphique de l'historique des stars pour davabase/whisper_real_time

Recherche par IA

Explorez plus de dépôts awesome

Décrivez vos besoins en langage naturel — l'IA classe des milliers de projets open source sélectionnés par pertinence.

Start searching with AI

Collections incluant Whisper Real Time

Sélections manuelles où Whisper Real Time apparaît.
  • Transcription de réunions en direct auto-hébergée
  • Outils de transcription vocale en temps réel
  • Moteurs de reconnaissance vocale open source

Alternatives open source à Whisper Real Time

Projets open source similaires, classés selon le nombre de fonctionnalités partagées avec Whisper Real Time.
  • cmusphinx/pocketsphinxAvatar de cmusphinx

    cmusphinx/pocketsphinx

    4,276Voir sur GitHub↗

    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

    Ccpythonspeech-recognition
    Voir sur GitHub↗4,276
  • guillaumekln/faster-whisperAvatar de guillaumekln

    guillaumekln/faster-whisper

    23,679Voir sur GitHub↗

    faster-whisper is an automatic speech recognition framework and an optimized implementation of the Whisper speech-to-text engine. It functions as a CTranslate2 inference engine designed to convert spoken audio into written text. The project serves as a model quantization tool that transforms large audio model weights into lower precision formats. This process reduces memory usage and increases execution speed on hardware by utilizing integer quantized weights. The framework covers a broad range of capabilities including batch audio transcription for parallel processing and voice activity det

    Python
    Voir sur GitHub↗23,679
  • buriburisuri/speech-to-text-wavenetAvatar de buriburisuri

    buriburisuri/speech-to-text-wavenet

    4,007Voir sur GitHub↗

    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

    Python
    Voir sur GitHub↗4,007
  • thewh1teagle/vibeAvatar de thewh1teagle

    thewh1teagle/vibe

    5,298Voir sur GitHub↗

    Vibe is a cross-platform transcription tool that converts spoken audio into text by running Whisper neural models directly on your device, with no cloud dependency. It can transcribe audio from files, microphones, system output, and network streams, and supports both batch processing of multiple files and real-time captioning from continuous input. Beyond basic transcription, Vibe identifies and labels different speakers through speaker diarization, and offers a choice of Command-Line Interface or HTTP API for automated and remote workflows. It also includes plugins to export transcripts to c

    TypeScriptaicross-platformdesktop
    Voir sur GitHub↗5,298
Voir les 30 alternatives à Whisper Real Time→

Questions fréquentes

Que fait davabase/whisper_real_time ?

Whisper Real-Time est un moteur de synthèse parole-texte conçu pour convertir l'entrée microphone continue en transcriptions écrites. Il fonctionne comme un processeur audio en temps réel qui tire parti du modèle OpenAI Whisper pour générer une sortie textuelle immédiate à partir de la langue parlée en direct.

Quelles sont les fonctionnalités principales de davabase/whisper_real_time ?

Les fonctionnalités principales de davabase/whisper_real_time sont : Whisper-Based Engines, Speech Recognition Engines, Real-Time Audio Transcribers, Speech-to-Text Engines, Speech Transcription Engines, Rolling Context Windows, Asynchronous Inference, Meeting Automation & Transcription.

Quelles sont les alternatives open-source à davabase/whisper_real_time ?

Les alternatives open-source à davabase/whisper_real_time incluent : cmusphinx/pocketsphinx — PocketSphinx is an offline speech recognition engine that converts raw audio from files or live microphone streams… guillaumekln/faster-whisper — faster-whisper is an automatic speech recognition framework and an optimized implementation of the Whisper… thewh1teagle/vibe — Vibe is a cross-platform transcription tool that converts spoken audio into text by running Whisper neural models… buriburisuri/speech-to-text-wavenet — This project is a deep learning framework designed for end-to-end speech-to-text transcription. It utilizes the… ufal/whisper_streaming — Whisper streaming is an automated speech recognition engine designed to convert live audio into text. It functions as… const-me/whisper — Whisper is a high-performance speech-to-text inference engine that uses graphics hardware shaders to accelerate the…