🎙️ Whisper

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

NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations
arxiv.org·23h
🗣️CMU Pronouncing
Taking the bitter lesson to heart for speech-to-speech models
metavoice.io·1d·
Discuss: Hacker News
🎧Learned Audio
How I Created a Voice AI Tutor with GPT-4 to Accelerate My Learning
hackernoon.com·19h
🗜️LZSS Variants
SoftWhisper simplifies audio and video transcription using Whisper model
github.com·13h·
Discuss: Hacker News
🎧Vorbis Encoding
When AI Doesn’t Understand You: A New Form of Global Inequality
undark.org·20h
🌍Cultural Algorithms
Training Specialist Models: Automating Malware Development
outflank.nl·8h
🧮SMT Solvers
How to Build 5 AI Apps with Just One API Key (LLMs, Image Gen, TTS, Translation & More)
dev.to·2h·
Discuss: DEV
🌀Brotli Internals
A Bilingual Benchmark Dataset and Evaluation Framework
thedailypimp.blogspot.com·12h·
Discuss: Hacker News
🔍Z3 Parsing
Parametric Matrix Models
nature.com·10h·
Discuss: Hacker News
📐Linear Algebra
AI Art Resources
jonathandinu.com·1h·
Discuss: Hacker News
🎧Learned Audio
Pushing the limits of long-context LLM training for 1M-token+ medical records
akasa.com·10h·
Discuss: Hacker News
🎵Audio ML
We're building a new global entertainment company (2024)
volleygames.com·1d·
Discuss: Hacker News
📞WebRTC
A deleted GitHub post gives an early look at OpenAI’s next major model, GPT-5
the-decoder.com·19h
⚙️Proof Engineering
Agentic AI: On Evaluations
towardsdatascience.com·9h
🧠Intelligence Compression
thewh1teagle/vibe
github.com·2d
💿FLAC Archaeology
[$] On the use of LLM assistants for kernel development
lwn.net·12h
🔩Systems Programming
GPT-5: Key characteristics, pricing and model card
simonwillison.net·10h·
Discuss: Hacker News
🖥️Modern Terminals
Built With Borrowed Hands
cra.mr·3h·
Discuss: Hacker News
⚡Proof Automation
DTPA: Dynamic Token-level Prefix Augmentation for Controllable Text Generation
arxiv.org·23h
📝Concrete Syntax
Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences
arxiv.org·1d
🗣️CMU Pronouncing