GitHub

Speech To Speech: Build local voice agents with open-source models

The pipeline provides a fully open and modular approach, with a focus on leveraging models available through the Transformers library on the Hugging Face hub. The code is designed for easy ...
decrypt

Meta Unveils New Tech That Uses AI to Translate Brain Activity Into Text—Without Surgery

Add Decrypt as your preferred source to see more of our stories on Google. Meta introduced Brain2Qwerty v2, a non-invasive AI system that decodes brain activity into text. The model achieved 61% ...

Attention Labs Launches SAA, the Engagement Control Layer That Lets Voice AI Know When It Is Being Addressed

SAA decides whether speech was meant for a device before it reaches the voice AI stack, so agents respond only when ...

Why Listen to AI Michael Caine Narrate ‘The Odyssey’ When Versions With Ian McKellen, Claire Danes and More Exist?

Emily Wilson is the first woman to translate the poem from Ancient Greek to modern-day English. Her rendition captures the ...

Kotoba Technologies Raises $10 Million in Seed Funding to Expand Real-Time Voice AI Platform Across East Asia

Kotoba Technologies, a developer of real-time speech models optimized for East Asian languages, today announced an additional ...

AI Humanizers Promise More ‘Human’ Writing—But Authenticity Is Hard To Capture

AI humanizers promise to make AI-generated text sound more natural. Learn how they work, why they're popular, and whether ...

Blast from the past as GIMP 0.54 is revived in Flatpak form

Development of GIMP has picked up speed in recent years, but now its first public release is back as a Flatpak, allowing the ...
GitHub

WenetSpeech-Yue: A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation

This is the official repository 👑 for the WenetSpeech-Yue dataset and the source code for WenetSpeech-Pipe speech data preprocessing pipeline. To address the unique linguistic characteristics of ...