Search Results for "speech processing"

...At only about 50 KB in size, the model is orders of magnitude smaller than typical audio super-resolution networks, yet it achieves high quality and realtime performance thanks to its compact architecture and efficient convolutional design. NovaSR is especially valuable for post-processing tasks in speech enhancement, TTS pipelines, and dataset restoration where low sampling rates degrade perceived audio clarity; the minimal model size also makes it suitable for edge and embedded use cases where memory is at a premium. Its performance can reach thousands of times realtime on modern GPUs, allowing massive audio batches to be processed with negligible compute overhead.

VCClient is a real-time voice conversion system that uses machine learning models to transform a speaker’s voice into another voice with minimal latency. It is designed for live applications such as streaming, gaming, and virtual communication, where immediate feedback is essential. The system supports multiple voice conversion models, including RVC and other neural network-based approaches, allowing users to switch between different voices or customize their output. It provides both a...

auto-subtitle is a Python-based command-line tool that automatically generates and overlays subtitles on video files using AI-driven speech recognition. It combines FFmpeg with OpenAI’s Whisper model to transcribe spoken audio into text and synchronize it with video playback. The tool processes video input, extracts audio, and produces subtitle files that can be either exported separately or burned directly into the final video output. It supports multiple transcription models with varying...

...It allows users to download videos or audio from YouTube and automatically generate subtitles or transcripts. The tool processes media locally, extracting audio and applying speech recognition to produce accurate text outputs. It supports multiple languages and can handle different Whisper model sizes, balancing performance and accuracy. yt-whisperc is designed for automation, enabling batch processing of multiple videos for transcription workflows. It also provides options for exporting subtitles in common formats such as SRT. ...

AutoSub is a Python-based tool designed to automatically generate subtitles for video or audio content using speech recognition technology. It processes media files by extracting audio, transcribing spoken content, and generating subtitle files in standard formats. The tool supports multiple languages and can integrate with translation systems to produce subtitles in different languages. It is designed for automation, allowing batch processing of multiple media files. ...

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.

Yet Another Audio Feature Extractor is a toolbox for audio analysis. Easy to use and efficient at extracting a large number of audio features simultaneously. WAV and MP3 files supported, or embedding in C++, Python or Matlab applications.

InproTK is an Incremental Spoken Dialogue Processing Toolkit, that is, a toolkit to help you build dialogue systems that listen and talk incrementally, allowing for advanced interactional behaviour. Please see our Wiki for more information: http://sourceforge.net/p/inprotk/wiki/

The purpose of HSVT is the collection and setup of OSS audio tools for the processing of speech and vocals. The end result will be something between jack-rack and ardour, with partial emulation or co-operation with hardware-rack voice processors.