与「LEC」相关的搜索结果

🌟Introducing🎻Violin — an Open-source Video Translation Skill. 📹Video is the dominant medium on the internet, yet most high-quality content (lecture, talk, podcast) is locked behind a single language, leaving global audiences behind. So we built Violin: a video skill that combines speech recognition, LLM translation, and speech synthesis into one seamless pipeline. 🌐 Demo: 📝 Blog: 🔗 GitHub: ✨Key Features: 🎙️High-quality multilingual ASR & Translation & TTS. 🗣️Personalize translation & voice (turn an academic talk into something children can follow). 💬Chat with the video — ask any questions grounded in the video. 🧩Support Web app, CLI, and Agent skill 🍃Fully open-source under MIT. ❤️Built with the wonderful @ShangZhu18 and advised by @james_y_zou ! All features powered by @togethercompute . Try it and let us know what you think! 🎻

#LEC# schedule update for all fans in Madrid and viewers at home: The showmatch between @IbaiLlanos & friends vs. a surprise guest team will take place at 12:30 (doors open 11:30), live from the arena. See you there!

Starting 🔜 the @NobelPrize lectures featuring our laureates - CEO @DemisHassabis and Research Director John Jumper - who will discuss their award-winning work on protein prediction and the journey to building #AlphaFold#. Tune in to watch from 9:50am GMT →

New (2h13m 😅) lecture: "Let's build the GPT Tokenizer" Tokenizers are a completely separate stage of the LLM pipeline: they have their own training set, training algorithm (Byte Pair Encoding), and after training implement two functions: encode() from strings to tokens, and decode() back from tokens to strings. In this lecture we build from scratch the Tokenizer used in the GPT series from OpenAI.