🏁 ¡¡𝗙𝗜𝗡𝗔𝗔𝗔𝗔𝗟 𝗗𝗘𝗟 𝗣𝗔𝗥𝗧𝗜𝗗𝗢𝗢𝗢𝗢!!
Gran victoria de nuestra @SEFutbol en el segundo partido de esta #CopaMundialFIFA.
⚽️ Goles de Lamine Yamal, Oyarzabal (x2) y Cucurella.
🇪🇸 🆚 🇸🇦 | 4-0 | 90+9’
#VamosEspaña
Stanford just hosted a hackathon. Over 1000 students from around the world came to build for 36 hours straight.
The reward? $100k+ in prizes.
Here are the winners and crowd standouts we saw at TreeHacks ‘24 @hackwithtrees (🧵):
Welcome OpenVoice! 🎙️
A versatile voice cloning approach that requires only a short audio clip from the reference speaker to replicate their voice and generate speech in multiple languages.
Open access weights 🔥
It enables granular control over voice styles, including emotion, accent, rhythm, pauses, and intonation, in addition to replicating the tone colour of the reference speaker.
They propose to use the base TTS (VITS) model to control the style and the language of the synthesised audio and a tone color convertor to embody prosody.
The base TTS model (VITS) was trained on 30K audio samples.
Tone color converter was trained on 300K audio samples.
Audio samples are scattered across - Chinese, Japanese & English.
Try it out on the Hugging Face space below! 👇