🎙️ Whisper

speech-to-text, model, local, whisper, whisper.cpp, input, voice, recognition, ai

Crystal 1.17.1 is released!
crystal-lang.org·1d
🔗Concatenative Languages
Architecting Your AI Data Pipeline Using B2 Overdrive
backblaze.com·12h
🌊Stream Processing
How AI Revolutionized Performance Engineering: Hours to Minutes Analysis
engineering.salesforce.com·11h
👁️System Observability
AI Safety Course Intro Blog
windowsontheory.org·2d
🔲Cellular Automata
Call Me a Jerk: Persuading AI to Comply with Objectionable Requests (2025)
papers.ssrn.com·1d·
Discuss: Hacker News
🔲Cellular Automata
Show HN: Sounds Social – A new platform to share and discover music and sounds
news.ycombinator.com·13h·
Discuss: Hacker News
💿FLAC Archaeology
AI in customer communication: the opportunities and risks SMBs can’t ignore
techradar.com·17h
🎯Recommendation Metrics
Give your AI agent superpowers with MCP
dev.to·1d·
Discuss: DEV
🔌Interface Evolution
Generative AI for Creative Storytelling (Without Losing Brand Identity)
dev.to·19h·
Discuss: DEV
📊Feed Optimization
NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech
arxiv.org·5d
🗣️CMU Pronouncing
Strategic Integration of AI Chatbots in Physics Teacher Preparation: A TPACK-SWOT Analysis of Pedagogical, Epistemic, and Cybersecurity Dimensions
arxiv.org·1d
🗺️Competency Maps
Who Said What? Build a Smart Transcriber Agent with AWS & LangChain
dev.to·2d·
Discuss: DEV
🎧WAV Metadata
You Watched It. Did AI Read It?
dev.to·1d·
Discuss: DEV
💿FLAC Archaeology
From Disagreement to Understanding: The Case for Ambiguity Detection in NLI
arxiv.org·1d
🎯Dependent Parsing
SOI Matters: Analyzing Multi-Setting Training Dynamics in Pretrained Language Models via Subsets of Interest
arxiv.org·1d
🤖Grammar Induction
Graph Convolutional Neural Networks to Model the Brain for Insomnia
arxiv.org·1d
🧠Neural Codecs
Moonshot's Kimi K2 Is a Hefty Contender to Claude, GPT-4 & Even Gemini
hackernoon.com·2d
🎬WebCodecs
AI chatbots remain overconfident—even when they're wrong, study finds
techxplore.com·11h·
Discuss: Hacker News
💻Local LLMs
CROSS-GAiT: Cross-Attention-Based Multimodal Representation Fusion for Parametric Gait Adaptation in Complex Terrains
arxiv.org·1d
📊Learned Metrics
Polynomial argmin for recovery and approximation of multivariate discontinuous functions
arxiv.org·1d
📐Error Bounds