This blog post is really cool: to understand everyday Transformers optimizations like KV cache, FlashAttention or PagedAttention: https://
astralord.github.io/posts/transfor
mer-inference-optimization-toolset/
… Image below is the interactive visualization for KB cache!
SOFTWARE
-
Everyday Transformers Optimizations: KV Cache, FlashAttention, PagedAttention
By
–
-
YouTube-Whisper: YouTube Video Audio Transcription with Whisper
By
–
Youtube-Whisper
— AK (@_akhaliq) 2 octobre 2024
A simple Gradio app that transcribes YouTube videos by extracting audio and using OpenAI’s Whisper model for transcription. Paste a YouTube link and get the video’s audio transcribed into text. pic.twitter.com/c6aNzjNYCiYoutube-Whisper A simple Gradio app that transcribes YouTube videos by extracting audio and using OpenAI's Whisper model for transcription. Paste a YouTube link and get the video's audio transcribed into text.
-
AI Trends: Quantum Computing, Copilot Updates, Productivity Gains
By
–
Prêts pour la crème de la crème de la Tech ? L'IA va remplacer les mauvais managers IBM ouvre le 1er datacenter quantique en Europe La FED doute des gains de productivité de l’IA Microsoft Copilot se refait une (vraie) beauté Julie Huguet, nouveau visage de la
-
GraphRAG-UI: User-Friendly Interface for RAG Text Indexing
By
–
GraphRAG-UI
— AK (@_akhaliq) 2 octobre 2024
GraphRAG-UI is a user-friendly interface for GraphRAG, a powerful tool that uses the Retrieval-Augmented Generation (RAG) approach to index and query large text data. This project supports the latest version graphrag-0.3.3 and aims to provide a convenient management… pic.twitter.com/davBb07LcBGraphRAG-UI GraphRAG-UI is a user-friendly interface for GraphRAG, a powerful tool that uses the Retrieval-Augmented Generation (RAG) approach to index and query large text data. This project supports the latest version graphrag-0.3.3 and aims to provide a convenient management
-
Real-time speech to speech with Whisper Turbo
By
–
real-time speech to speech with whisper turbo https://t.co/8qDGac419x
— AK (@_akhaliq) 1 octobre 2024real-time speech to speech with whisper turbo
-
Real-time Speech to Speech with Whisper-Turbo Technology
By
–
real-time speech to speech with whisper-turbo: https://t.co/8qDGac419x
— AK (@_akhaliq) 1 octobre 2024real-time speech to speech with whisper-turbo:
-
Realtime Voice API cost to halve every few months, predicts user.
By
–
Betting the cost of Realtime Voice API will be cut in half every few months.
-
AI-Powered Meeting Summarizer: Audio Transcription and Summarization Tool
By
–
AI-Powered Meeting Summarizer The AI-Powered Meeting Summarizer is a Gradio-powered application that converts audio recordings of meetings into transcripts and provides concise summaries using whisper.cpp for audio-to-text conversion and Ollama for text summarization. This tool
-
Model Distillation: Compressing Larger AI Models Efficiently
By
–
Model "Distillation": Compress larger models to smaller versions Cool. Do you know more about it?
-
OpenAI Releases Realtime API, Vision Fine-tuning, Prompt Caching
By
–
realtime api (speech-to-speech): https://
openai.com/index/introduc
ing-the-realtime-api/
… vision in the fine-tuning api: https://
openai.com/index/introduc
ing-vision-to-the-fine-tuning-api/
… prompt caching (50% discounts and faster processing for recently-seen input tokens): https://
openai.com/index/api-prom
pt-caching/
… model distillation (!!): https://
openai.com/index/api-mode
l-distillation/
…