Running on Zero Featured 101 Echo-TTS Preview π’ 101 Fast, multi-speaker TTS (44.1kHz) with voice cloning
Running 31 Korean Open Source Heatmap π₯ 31 Explore Korean AI open source contributions and releases
view article Article Small Yet Mighty: Improve Accuracy In Multimodal Search and Visual Document Retrieval with Llama Nemotron RAG Models 22 days ago β’ 20
LTX-2: Efficient Joint Audio-Visual Foundation Model Paper β’ 2601.03233 β’ Published 22 days ago β’ 137
view article Article Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR 23 days ago β’ 71
view article Article The Engineering Handbook for GRPO + LoRA with Verl: Training Qwen2.5 on Multi-GPU 26 days ago β’ 12
view article Article Tokenization in Transformers v5: Simpler, Clearer, and More Modular +4 Dec 18, 2025 β’ 118
view reply Hi @kyars is there any part that you think i can improve upon or is it everything?would appreciate any feedback!