Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
See and hear your colleagues in true-to-life size and sound, making hybrid meetings feel more inclusive and connected.
Announcing new voice capabilities in Gmail, Docs and Keep, a new design tool called Google Pics and updates to AI Inbox.
Dataset com 10 mil – 100 mil exemplos — 89.1 mil downloads no Hugging Face. FLEURS Fleurs is the speech version of the FLoRes machine translation benchmark.
Our newest audio model introduces granular audio tags that give you precise control to direct AI speech for expressive audio generation.
Modelo de geração de vídeo — 2.2 mi downloads e 1.7 mil curtidas no Hugging Face.
Modelo de síntese de voz — 347.2 mil downloads e 1.2 mil curtidas no Hugging Face.
Duration-aware scheduling policies improve ASR serving latency by leveraging audio length as a predictor for processing time, with SJF and HRRN algorithms showing significant media…
Modelo de síntese de voz · 1.7 B de parâmetros — 2.5 mi downloads e 1.8 mil curtidas no Hugging Face.
Dataset em destaque no Hugging Face — 31 downloads. 🧠 Mental Association Dataset (200k Global Responses) Dataset Summary This dataset explores mental associations, the intuitive connections people ma…
Dataset em destaque no Hugging Face — 35.1 mil downloads. GAIA dataset GAIA is a benchmark which aims at evaluating next-generation LLMs (LLMs with augmented capabilities due to added tooling, efficient promp…
Modelo de síntese de voz · 82 M de parâmetros — 10.9 mi downloads e 6.5 mil curtidas no Hugging Face.
Modelo de reconhecimento de fala — 8.2 mi downloads e 2.6 mil curtidas no Hugging Face.