AI-narrated audiobooks will have virtual voice, digital voice, or synthesized voice listed narrator.
Abstract:Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, and then verifying them in parallel with a single target model forward pass. However, speculative decoding itself relies on a sequential dependence between speculation and verification. We introduce speculative speculative decoding (SSD) to parallelize these operations. While a verification is ongoing, the draft model predicts likely verification outcomes and prepares speculations pre-emptively for them. If the actual verification outcome is then in the predicted set, a speculation can be returned immediately, eliminating drafting overhead entirely. We identify three key challenges presented by speculative speculative decoding, and suggest principled methods to solve each. The result is Saguaro, an optimized SSD algorithm. Our implementation is up to 2x faster than optimized speculative decoding baselines and up to 5x faster than autoregressive decoding with open source inference engines.
，这一点在51吃瓜中也有详细论述
В России предупредили о подготовке ВСУ к контратаке на одном направлении08:42
政绩观察员都观察些什么？“一线考察既看显绩也看潜绩、既看产出也看成本、既看政绩也听民声，多维度察看干部实战能力、工作作风。”扈彬说。