speach-recognition

A tool for summarizing dialogues from videos or audio

Versatile framework designed to streamline the integration of your models, as well as those sourced from Hugging Face, into complex programs

Robot niko with raspberry pi and python

A small script that types what you say using whisper while holding a hotkey

ROS2 STT node. An out of the box speach to text recognizer using standalone Vosk speech recognition toolkit. This is a MIRRORED REPOSITORY Refer to the GitLab page for the origin.

简单的whisper语音转文字（STT）快捷语音输入Windows系统悬浮窗。录音自动复制到剪切板。本地部署模型版，数据更安全

This is a web application is created with the aim to provide quality education through AI.

🎤 Easy to use, speach-to-text with shortcut to start, auto-paste transcribed text, Python AI-powered

AI Personal Desktop Assistant built using python libraries. It does almost anything, including sending emails, Opens any website with just a voice command, Plays Music, and Wikipedia searching.

OpenAI-compatible ru speech recognition service

Text-to-Speech & AI Bot With OSC Integration

SwarSathi makes communication accessible for people with hearing and speech impairments in India. Over 70 million people can benefit from this platform!

gA easy to install/use speach recognition using a webUI with Gradio and faster wisper models (guillaumekln/faster-whisper-large-v2 Is the default)

This is a simple speech recognition algorithm. This was a Learning Project, in which I learned how to apply machine learning to sounds, using concepts like Mfcc and the role of Fourier transform.

An application which contains an AI chatbot, AI code generator and an AI image generator

automate telegram account voice to text

Description The Voice Assistant is a powerful tool designed to interact with users through voice commands, providing a seamless and intuitive way to perform tasks, obtain information, and control applications. This project demonstrates the integration of speech recognition and synthesis technologies to create a responsive and user-friendly voice in

A Python-based voice-controlled AI assistant (Jarvis) that uses speech recognition, Google Gemini AI, and automation to handle web searches, system control, messaging, weather, calendar events, and more — all by voice.

Multilingual Streamlit application for translation, transliteration, speech-to-text, text-to-speech, and interactive machine-learning model evaluation.

Analysis of prosodic features as predictors of ASR difficulty and their use in curriculum learning strategies.