Nvidia Parakeet-TDT-0.6B-v2 — a New LLM for Audio Transcription
On May 1, 2025, Nvidia introduced Parakeet-TDT-0.6B-v2, a language model designed for automatic speech recognition…
Category: Blog
Voice Interface to LLM: How We Created AI Confession Room
While OpenAI delays the release of audio modality for ChatGPT, we decided to share our…
Subtitles for YouTube Without the Cloud: Open-Source Tools for Local Generation
Creating subtitles for YouTube usually involves using cloud services such as automatic generators from Google…
How to Quickly Convert Audio and Video Interview Recordings into Text Using Neural Networks
Every journalist, copywriter, and blogger knows how tedious it is to process interviews. Transcribing recordings…
Subtitld: a Simple Open-Source Subtitle Editor with a Visual Timeline
Subtitle Edit is a powerful and convenient tool designed for creating and editing subtitles. The…
Automatic Subtitling with AI: Time Savings and Accuracy
Modern speech recognition technologies allow you to fully automate the process of creating subtitles for…
Automatic Translation of Transcripts
Whishper provides a convenient way to not only transcribe audio files, but also automatically translate…
Choosing Between Accuracy, Speed, and Resources
Whisper offers five different Whisper models, each with different accuracy and size. These models are…
Accelerating Whishper with GPU: CUDA Configuration and Support
Starting with version 2.0.0, Whishper supports GPU usage, which significantly speeds up the process of…
Creating a New Transcription
Creating a new transcription in Whishper is very easy, even if you have never used…