There are 12 repositories under audio-to-text topic.
The open-source iOS app that's making quality voice transcription more accessible on mobile devices.
Simple web application, which can be used to convert audio to subtitles by OpenAI's Whisper model
Tero Subtitler is an open source, cross-platform, and free subtitle editing software.
This repository contains a Python script that allows users to download the audio from a YouTube video, transcribe it into text, detect the language and save the transcription in txt file automatically.
A desktop application that transcribes audio from files, microphone input or YouTube videos with the option to translate the content and create subtitles.
Use Whisper to convert audio files into LRC subtitle files in bulk. 使用whisper实现将音频文件批量转换为lrc字幕文件
Simple Python audio transcriber using OpenAI's Whisper speech recognition model
Persian ASR dataset
core shell functions building blocks for advanced AI pipelines
Generate text captions for audio files & youtube video using OpenAI Whisper on Google Colab. Multiple languages support.
A SwiftUI App For People Who Need To Take Down Important Information Quickly.
Chrome Extension to capture captions of ongoing meetings by using webkitspeechrecognition api for all the web video conferencing platforms (for google meet, it directly extracts the captions) and sends to flask api for summarization.
Develop a python application that allows you to extract valuable insights, engage in meaningful conversations, and explore video content in a whole new way.
An efficient desktop application for transcribing audio files into text using Vosk speech recognition.
AudioInsight is a web application that processes audio and generates transcriptions, summaries, titles, and allows users to ask questions about the related audio.
GUI Showcase of using Whisper to transcribe and analyze Youtube video
An application in which you can record the output audio stream and turn it into text format.
Extract textual meaning and knowledge from all videos of a YouTube user's playlists
Transcribe Audio to Text with node.js using the Whisper model from OpenAI.
streamlit app to transcript audio to text using openai's whisper library
Open-source AI library (audio to text, simple NLP and algorithms)
Implemented some of the models and techniques learned in NLP to help build systems that help in daily life.
Transform audio recordings into text transcripts effortlessly with AudioTranscribe! 🎙️📝 Simplify your transcription process and enhance accessibility with top-notch accuracy. Explore the power of text-to-speech conversion today! 🚀🎧
I have used the Google Cloud Vision API to transcript the audio file and extract the text from the image.
Event-driven AI > A Python-Kafka event-driven micro-services solution for distributed audio transcriptions.
Edge AI > AI app to easily perform transcriptions on regular computers. Quality on par with on-cloud alternatives. Lower costs. Reduced privacy risks.
Timestamped ASR microservice
WER, MER, WIL of Whisper vs Vosk vs Google transcribators comparator
📼 A streamlit web interface designed to extract words from video/audio files into text • Python, FFmpeg, Whisper, YT-DLP
There is simple backend project to use whisper-rs.
Whisper Large V3 is a pre-trained model developed by OpenAI and designed for tasks like automatic speech recognition (ASR), speech translation and language identification.
Transcribe Bangla Audio into Text