Qwen-TTS now speaks dialects: new Alibaba speech synthesizer

Alibaba Cloud has updated Qwen-TTS, a text-to-speech model that supports 3 Chinese dialects (Pekingese, Shanghainese, Sichuanese) and 7 bilingual Chinese-English voices. The model achieves human-level naturalness and expressiveness, available via Qwen API.

Alibaba/Qwen

Comparison of Large Language Model Architectures: From DeepSeek V3 to OLMo 2

Sebastian Raschka compares the architectures of modern LLMs, including DeepSeek V3 with Multi-Head Latent Attention and Mixture-of-Experts, and OLMo 2 from the Allen Institute for AI with Post-Norm and QK-norm. The article covers key architectural decisions such as Grouped-Query Attention and various normalization schemes.

DeepSeek Allen Institute for AI