这两周分享不了少 TTS 的模型
下周开始陆续分享一些 ASR/STT 的模型 之前看大家对 Whisper 多少有点恨铁不成钢
下面会陆续发一些 Whisper 的变种版
MACHINE LEARNING
-
Sharing TTS and ASR/STT Model Variants Including Whisper
By
–
-
DeepSeek Achieves Frontier Model with 1% Previous Compute
By
–
Deepseek trained a frontier model using 1% of previous compute.
-
Matrix Calculus for Machine Learning and Beyond Paper
By
–
Matrix Calculus (for Machine Learning and Beyond) Paige Bright, Alan Edelman, Steven G. Johnson: https://
arxiv.org/abs/2501.14787 #ArtificialIntelligence #DeepLearning #MachineLearning -
Matrix Calculus for Machine Learning and Beyond
By
–
Matrix Calculus (for Machine Learning and Beyond) Paige Bright, Alan Edelman, Steven G. Johnson: https://
arxiv.org/abs/2501.14787 #ArtificialIntelligence #DeepLearning #MachineLearning -
Paint Hundreds Not Masterpieces Iterative Practice Over Perfection
By
–
A painter I like has advice to people to paint a particular part by the hundreds. Approximately: “Don’t get attached! You can buy a hundred for $10. These aren’t works of art! They are practice pieces! Your job is not to save them! It is to put paint on all of them!”
-
Hourglass Diffusion Transformers Enable Scalable High-Resolution Image
By
–
Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers Crowson et al.: https://
arxiv.org/abs/2401.11605 #ArtificialIntelligence #DeepLearning #MachineLearning -
Google’s Gemini, Gemma, and JAX Stack Impress AI Observer
By
–
Un ponte de l'IA. Nous avions analysé son papier. Traduction : Google n’a jamais été doué pour le marketing de ses produits, mais alors niveau technologie, c’est du très lourd. Très optimiste sur Gemini, la gamme de modèles open source Gemma, et la stack JAX/Keras/TPU.4o
-
Google’s Marketing Weakness Versus Strong Technology Leadership
By
–
Google has never been good at marketing its products, but boy is it good at technology. Very bullish on Gemini, the Gemma line of open models, and the JAX/Keras/TPU stack
-
Google Releases RecML: JAX-Optimized Recommender Systems Library
By
–
Google quietly released a powerful recommender systems library optimized for JAX and TPUs, based on Keras. It's called RecML. It has native support for SparseCore (latest hardware for handling large distributed embeddings)
-
Data Scaling Laws for End-to-End Autonomous Driving Systems
By
–
Data Scaling Laws for End-to-End Autonomous Driving This paper explores how scaling training data affects performance in end-to-end autonomous driving systems, evaluating data efficiency and scaling laws with a unified, differentiable model. Problem: Modular autonomous driving