Projects sharing features with Faster Whisper

This project is a high-throughput transcription engine and PyTorch inference wrapper designed to convert spoken audio files into text using the OpenAI Whisper model. It functions as a hardware-accelerated speech-to-text transcriber that runs locally on a user's machine. The system focuses on AI model performance tuning to maximize hardware throughput. It utilizes GPU acceleration, half-precision floating point tensors, and Flash-Attention to reduce processing time and memory overhead during transcription. The implementation covers large-scale transcription workflows and local speech-to-text

Chenyme-AAVT is an AI-powered video transcription tool and translation platform. It converts speech from media files into editable text transcripts using speech recognition models and voice activity detection to ensure accurate phrasing and timing. The system functions as a content generator that transforms video transcripts into structured blog posts and marketing graphics using large language models. It also includes a subtitle formatting editor that allows for the modification of subtitle styles with a real-time video preview. The platform provides multilingual translation capabilities th

WhisperX is an automated speech recognition toolkit designed to convert spoken audio into text while maintaining precise synchronization with the original media. It functions as an integrated pipeline that combines transcription, phoneme-based alignment, and speaker diarization to produce structured, attributed transcripts. The project distinguishes itself through its use of forced alignment, which matches existing text to audio signals at the phoneme level to generate accurate word-level timestamps. It also incorporates speaker diarization to identify and label unique voices within a recordi

This is a Windows application for automatic speech recognition that transcribes spoken audio from video files into timestamped SRT subtitle files. It serves as a subtitle generator and translation tool that converts media speech into synchronized text. The software functions as a batch media transcriber, allowing the simultaneous processing of multiple audio and video files to generate subtitles in bulk. It includes a translation workflow to convert transcriptions between different languages for the creation of bilingual or localized files. The system also provides text refinement capabiliti

Autosub is a command-line media processor and automatic subtitle generator that converts audio streams from video and audio files into timed text overlays. It functions as an AI speech-to-text converter that uses OpenAI Whisper to generate synchronized subtitles. The tool includes a language translation pipeline to convert transcribed speech into target languages, enabling multilingual video captioning. It manages the process from audio-stream extraction to the serialization of final subtitle files for local storage. The system covers audio-to-text transcription, time-stamped text mapping, a

WhisperLive is a real-time speech-to-text server that converts live audio streams into text using Whisper models. It functions as a backend service that receives microphone input via WebSockets and provides incremental transcriptions with word-level timestamps. The system utilizes a GPU-accelerated inference engine and a keyword-boosted transcription API to improve the recognition accuracy of domain-specific jargon, acronyms, and product names. It also includes a speaker diarization tool that clusters audio embeddings to identify and label different participants within a recording. Additiona

Whisper is a high-performance speech-to-text inference engine that uses graphics hardware shaders to accelerate the transcription of spoken audio into written text. It implements a GPU-accelerated automatic speech recognition framework specifically designed to run Whisper models. The system focuses on high-speed processing for both recorded audio files and live microphone streams. It utilizes voice activity detection to analyze raw audio in real time, triggering the inference engine only when human speech is detected. The engine covers a broad range of capabilities including real-time audio

This project provides a self-hosted server for automatic speech recognition, functioning as a containerized inference engine for the Whisper model. It exposes core transcription and translation capabilities through a standardized web interface, allowing for the integration of speech-to-text services into external applications. The service distinguishes itself by incorporating advanced audio analysis tools, including speaker diarization to attribute text to specific individuals and voice activity detection to filter non-speech segments. It supports automated language detection and provides out

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

VideoCaptioner is an automated tool designed to generate and embed time-synchronized subtitles into video files. By leveraging speech recognition models, the software converts spoken audio into text and calculates precise timestamps to ensure captions align with the original media. The project operates as a local-first inference pipeline, performing all transcription tasks on the host machine to maintain data privacy. It utilizes a transformer-based neural network for speech recognition and integrates a multimedia framework to handle the technical aspects of video processing and subtitle stre

VideoLingo is an automated video localization suite designed to transcribe, translate, and dub video content. It functions as a translation pipeline that utilizes large language models to convert spoken audio into precise text segments and translate them into multiple languages. The system differentiates itself through a multi-step translation refinement process and a specialized natural language processing utility that segments text into single-line captions meeting broadcast standards. It also integrates synthetic voiceover generation to replace or augment original audio tracks. The projec

This project is an AI video post-production suite that uses large language models and programmatic tools to automate editing, transcription, and subtitle generation. It functions as an AI editing agent that translates natural language instructions into shell commands, providing a programmatic interface for manipulating media via FFmpeg. The toolkit includes a motion graphics engine that generates technical animations and visual overlays through code-driven rendering and mathematical definitions. It distinguishes itself by combining an AI-powered transcriber for word-level timestamps with an a

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

llama.cpp is a high-performance C++ inference engine and runtime for executing large language models locally across various hardware architectures. It provides the core components for local model execution, including a dedicated model quantizer for compressing weights into the GGUF format and a system for generating text embeddings for semantic search. The project distinguishes itself through specialized memory and execution optimizations, such as block-wise weight quantization to reduce memory footprints and memory-mapped model loading. It supports structured text generation by using formal

This project is a quantized fine-tuning framework for large language models. It implements a low-rank adaptation library and a four-bit quantizer to reduce the GPU memory requirements needed to train large models. The framework utilizes four-bit quantization and low-rank adapters to enable model training on consumer-grade hardware. It further reduces the memory footprint through double quantization and a paged optimizer that offloads states to system RAM. The system supports distributed training across multiple GPUs to handle larger parameter scales and includes utilities for custom dataset

This is a tool for downloading videos, images, and audio from the Douyin social media platform using shareable URLs or profile links. It can download individual posts, entire user profiles including all posts and liked content, collections, and music tracks, with options for watermark-free and high-quality output. The tool also supports live stream recording, comment collection, and keyword-based content search with JSONL export. The project distinguishes itself through an integrated REST API server that accepts download and transcription requests, tracks job status, and exposes health check

This project is a comprehensive toolkit for on-device speech recognition, synthesis, and audio processing, specifically engineered for Apple Silicon. It provides a framework for building real-time, full-duplex voice agents that operate entirely offline, leveraging native hardware acceleration to maintain performance and privacy. By utilizing optimized machine learning models, the library enables local execution of complex audio tasks without reliance on external cloud services. The library distinguishes itself through its specialized focus on local, high-performance voice interaction. It incl

Kaldi is an automatic speech recognition toolkit used to train and deploy models that convert spoken audio into text. It functions as a framework for designing and evaluating acoustic and language models through a structured pipeline of processing tools. The system acts as a cross-platform speech engine, capable of compiling recognition logic for Android and WebAssembly to enable execution on mobile devices and web browsers. It also includes a dedicated converter for migrating speech recognition models from the HTK format into a compatible internal structure. The toolkit covers a broad range

Omi is an open-source wearable AI platform that captures audio and screen data to provide real-time conversational assistance and memory. It integrates a wearable hardware development kit with a vector memory database and large language model capabilities to create a persistent digital record of user interactions. The platform is distinguished by its BLE audio streaming pipeline, which transmits raw audio from wearable hardware for real-time transcription and speaker identification. It utilizes a plugin-based agent tool framework that allows AI assistants to autonomously invoke custom functio

Sherpa-ONNX is an ONNX-based speech processing toolkit that provides a local speech recognition engine, an on-device voice synthesis tool, and a speaker identification framework. It is designed as a cross-platform speech API that enables speech-to-text, text-to-speech, and speaker verification tasks to be executed locally on a device without requiring network access. The project is distinguished by its ability to perform zero-shot voice cloning and speaker diarization on-device. It supports a wide range of hardware accelerations, including GPU and various NPU architectures, and provides a Web

Yi is a bilingual language model and foundation model designed for natural language processing, reasoning, and reading comprehension in both English and Chinese. It is built as a transformer-based architecture capable of general purpose text generation and conversational tasks. The model is distinguished by its ability to function as a long context system, processing and analyzing extended input sequences up to 200k tokens. It also supports quantized versions that use low-bit precision to reduce memory footprints, enabling execution on consumer-grade hardware. The project covers a broad rang

Daft is a distributed dataframe library and multimodal data processor designed to handle large-scale structured and unstructured data. It functions as a vectorized execution engine that processes tables alongside images, audio, and video, utilizing a unified schema to manage diverse data types. The project distinguishes itself by combining distributed data engineering with large-scale AI inference. It provides an AI data pipeline for batch-optimizing model prompts and generating high-dimensional text embeddings, while utilizing zero-copy memory sharing to execute custom Python functions witho

This project is a framework for developing multimodal AI agents that function as programmable participants in real-time communication rooms. It enables the construction of agents that can see, hear, and speak by integrating speech-to-text, large language models, and text-to-speech pipelines to facilitate low-latency, natural conversations. The system is distinguished by its advanced orchestration of real-time media and conversational flow, including support for full-duplex speech, preemptive response generation, and sophisticated interruption management. It further differentiates itself throu

The Gemini Cookbook is a comprehensive collection of implementation patterns, code samples, and development guides designed for building applications with Google Gemini models. It serves as a central resource for developers to integrate multimodal generative artificial intelligence into their software, providing the necessary frameworks to manage model interactions, stateful workflows, and structured data extraction. The repository distinguishes itself by offering specialized toolkits for autonomous agent orchestration, enabling the construction of agents that can execute code, browse the web

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech systems. It utilizes a frame-based data pipeline to route audio, video, and text through a modular sequence of processors, enabling the orchestration of low-latency conversational AI. The project is distinguished by its ability to coordinate complex multimodal services, including speech-to-text, language models, and text-to-speech, within a single pipeline. It features semantic voice activity detection for natural turn-taking, state-machine conversation flows for dialogue manag

LiveKit is a comprehensive framework for building and orchestrating real-time, multimodal AI agents that interact with users through voice, video, and text. It provides a centralized, event-driven architecture to manage the entire lifecycle of automated participants, from initialization and session state management to graceful shutdown. By utilizing a selective forwarding unit, the platform efficiently routes media streams between participants and agents, ensuring low-latency communication and secure, token-based authentication for all connections. The platform distinguishes itself through it