Decrypt

Leaks Reveal Suno Fed Thousands of Hours of Deezer, YouTube and Pond5 Data Into Its AI

Leaked source code reveals how AI music company Suno actually assembled substantial portions of its training library.
MUO on MSN

I transcribed hours of audio offline with a free model, and it nailed it

I finally uncovered the secret to transcribing hours of audio offline without uploading to third-party servers.
marktechpost

Interfaze Ships diffusion-gemma-asr-small, an Open-Source Diffusion ASR Model Transcribing Six Languages via DiffusionGemma’s Parallel Denoising Decoder

Interfaze, a young YC’s startup, has open-sourced a new speech recognition model. It is called diffusion-gemma-asr-small. The model transcribes audio through a diffusion decoder, not an autoregressive ...
note

The story of how an IT guy realized voice recognition that AI said was impossible

Hello, I am an IT guy who can't quite become a farmer. In my previous article, I wrote about how I got voice recognition working on a Raspberry Pi alone. When I shout "tomato," vegbook returns ...
GitHub

taisei-zoo/local-transcribe-gijiroku-shared

local-transcribe-gijiroku-shared は、同一ネットワーク内の共有フォルダーをキューとして利用し、複数人から登録された文字起こし・文書抽出・ローカルLLM要約依頼を、サーバー側端末で順次処理 ...
GitHub

A Python tool that uses Google Gemini API to transcribe video or audio files into SRT subtitle files.

⚙️ TOML Configuration Support: Comprehensive configuration management system with multiple sources. 📝 Configuration file support with automatic search in multiple locations 🔄 Multi-source ...