daishir0/WhisperTranscribeKit

Stars
1
Language
HTML
License
MIT License
Created about 1 year ago
Updated about 1 year ago

daishir0/WhisperTranscribeKit

daishir0

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

WhisperTranscribeKit: A real-time audio transcription toolkit using OpenAI's Whisper model, built with Flask and WebSocket.

kindle2ss

This tool automatically takes screenshots of your Kindle screen and saves them as files.

AudioTranscribePro

AudioTranscribePro is a powerful Python-based tool that combines audio transcription with speaker diarization. It processes various audio file formats (MP3, M4A, MP4), converts them to WAV, transcribes the content, and identifies different speakers in the audio.

saizeriya

A script designed for image alignment and difference detection. It aligns two input images using feature point matching and homography, then computes and marks the differences between them. The script uses OpenCV and skimage for image processing. It is useful for comparing two similar images to detect subtle changes.

VideoCompressor

A script to compress video files using ffmpeg with customizable parameters.

pdf2txt

"pdf2txt" is a simple, lightweight tool designed to extract text from PDF files and clean it by removing line breaks and unnecessary spaces. It uses the pdfminer library for text extraction and provides a clean, readable text output. Ideal for quick conversions and text processing tasks.

RealtimeWhisper

RealtimeWhisper is a Python script that captures audio in real-time, transcribes it using OpenAI's Whisper ASR system, and uploads the transcriptions to a remote server via SSH.