Aleph's silent-speech prototype reads tongue motion at 15.6% word error rate
The research lab says a 50-hour dataset let its prototype decode open-vocabulary speech, with hardware still stuck at probe-and-gel stage.
Read the full articleYou might also wanna read
NanoGPT Slowrun Achieves 10x Data Efficiency Breakthrough in Language Model Training
We've achieved 10x data efficiency with NanoGPT Slowrun within a few weeks. An ensemble of 1.8B parameter models (18B total params) trained
OpenWispr: A Local Open-Source AI Speech-to-Text Model
Turn your voice into formatted text. It's open source and runs 100% locally. 3-5x faster than typing, and especially helpful when prompting
Product Hunt·11mo ago
Local Audio Transcription with Python and OpenAI Whisper: Privacy-Focused Guide
Learn how to extract text from audio files locally using Python, Whisper, and other powerful tools. Complete setup guide with practical exam
pavlinbg.com·9mo ago
Cohere releases open-source 2B parameter Arabic ASR model with dialect and code-switching support
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
CraneAI Labs Releases v1.2 of Streaming ASR Model for Luganda, Shona, and Swahili
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Research Directions for Overcoming Memory and Interconnect Challenges in Large Language Model Inference Hardware
Large Language Model (LLM) inference is hard. The autoregressive Decode phase of the underlying Transformer model makes LLM inference fundam
arxiv.org·5mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.