view post Post 1842 did a small emotive classified test dataset for all the tts tuners out there MrDragonFox/Elise3h total mit - single speaker voicedataset is a copy of an existing one just added the emotional tags over 1200 samples - should be good enough to test if emotional tags stick in your finetune See translation 1 reply Β· π 12 12 π 2 2 + Reply
DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping Paper β’ 2502.20900 β’ Published Feb 28 β’ 9
microsoft/Phi-4-multimodal-instruct Automatic Speech Recognition β’ Updated 2 days ago β’ 956k β’ 1.28k
Running 2.44k 2.44k The Ultra-Scale Playbook π The ultimate guide to training LLM on large GPU Clusters
Running 176 176 Ebook2audiobook v25.3.22 π Turn any ebook into audiobook, 1107+ languages supported!
Running on Zero 478 478 Finegrain Object Cutter β Create high-quality HD cutouts with just a text prompt