Distill Whisper exhibits fewer 'hallucination errors' in transcribing long audio, crucial for customer service and accessibility. Its detailed training underscores the efforts to enhance AI efficiency.
@whats_ai
-
AI Voice Interaction Evolution: Whisper and Distill Whisper Advances
By
–
AI voice interaction is evolving to match text communication. @OpenAI
's Whisper converts voice to text effectively, and Distill Whisper by @huggingface now offers similar accuracy with increased speed and less complexity. -
Distill Whisper: 99% Accuracy with 2% Data for Real-Time Voice AI
By
–
Distill Whisper uses knowledge distillation to train a smaller model to achieve 99% accuracy of a larger one with 2% data, aiming for real-time AI voice applications without delays.
-
Improving Remote Team Communication at Google DeepMind
By
–
Improving (remote) team communication and collaborations at Google DeepMind
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 16 décembre 2023
What do you think about such async updates?
From my episode with @DynamicWebPaige from @GoogleDeepMind :https://t.co/7yI3yWhgFH pic.twitter.com/YItjUKXr2eImproving (remote) team communication and collaborations at Google DeepMind What do you think about such async updates? From my episode with @DynamicWebPaige from @GoogleDeepMind : https://
youtu.be/y5nxMnTtbD4 -
Fine-tuning LLM into Specialized Financial Expert
By
–
Good morning fellow AI enthusiast! This is the last video in our series on training and fine-tuning your LLM built for the course with @towards_AI and @activeloop
! We are transforming a generalist LLM into a specialized financial expert! https://
open.substack.com/pub/louisbouch
ard/p/how-to-fine-tune-your-llm-on-tweets?r=25qlky&utm_campaign=post&utm_medium=web&showWelcome=true
… -
Fine-Tuning Large Language Models on Investment Tweets
By
–
How to Fine-Tune your LLM on Tweets! (large language models for investing)
-
Stable Diffusion: Training AI with Images and Text
By
–
Qu’est-ce que Stable Diffusion (entraîner une IA avec images et texte)
— Louis-François Bouchard 🎥🤖 (@Whats_AI) 14 décembre 2023
Apprenez-en davantage dans la vidéo complète: https://t.co/FYAmhAv8AV
Abonnez-vous à la chaîne pour soutenir mon travail de vulgarisation en français!#ia #IntelligenceArtificielle #technologies pic.twitter.com/CKC6lbW04PWhat is Stable Diffusion (training AI with images and text) Learn more in the full video:
https://youtu.be/s6WPC8eYrTM?feature=shared
… Subscribe to the channel to support my work in science communication in French! #ai #ArtificialIntelligence #technology -
New Series: Demystifying Psychological Terms in AI with Auxane Boch
By
–
We also have an essential new series where Our great ethicist, Auxane Boch, will introduce and demystify the most used (psychological) terms in the AI space that are often times misused. Learn more in this week's iteration: https://
open.substack.com/pub/louisbouch
ard/p/reinforcement-learning-from-human?r=25qlky&utm_campaign=post&utm_medium=web
… -
RLHF and RLAIF: Training LLMs with Human and AI Feedback
By
–
Good morning fellow AI enthusiast! This is the seventh video of my LLM series for our free course "Training & Fine-Tuning LLMs for Production"! In this really exciting one, we dive into RLHF and its recent alternative RLAIF, where humans are once again replaced by more AI!
-
Learn Prompting Resource Recommendation and Endorsement
By
–
The @learnprompting resource? If you are referring to this of course it is!