Researchers found and mapped four seamounts in the deep sea off the coast of Peru and Chile. The tallest of these new peaks rises around 1.5 miles above the seafloor.

100-feet tall, Tor Alva will likely be the world’s tallest building by the end of 2024.

Switzerland, home to the tallest summit in Europe — Jungrau, will also be home to one of the world’s tallest 3D-printed structures.

Drake Motor Partners developed the dealership last year and now sold it for $23.7 million.

Authorities in Virginia are investigating the cause of a house explosion and fire that killed one firefighter, injured 10 others and leveled a home in a Washington, D.C., suburb.

Audio samples for the paper “BASE TTS: Lessons from building a billion-parameter text-to-speech model on 100K hours of data”

Abstract: We introduce a text-to-speech (TTS) model called BASE TTS, which stands for Big Adaptive Streamable TTS with Emergent abilities. BASE TTS is the largest TTS model to-date, trained on 100K hours of public domain speech data, achieving a new state-of-the-art in speech naturalness. It deploys a 1-billion-parameter autoregressive Transformer that converts raw texts into discrete codes (“speechcodes”) followed by a convolution-based decoder which converts these speechcodes into waveforms in an incremental, streamable manner. Further, our speechcodes are built using a novel speech tokenization technique that features speaker ID disentanglement and compression with byte-pair encoding. Echoing the widely-reported “emergent abilities” of large language models when trained on increasing volume of data, we show that BASE TTS variants built with 10K+ hours and 500M+ parameters begin to demonstrate natural prosody on textually complex sentences.