This work represents an important step forward for this field of research. Just as other work has done for images + text, we believe the generalization & scalability of Voicebox could usher in a new era of generative AI for speech — we're excited to continue pushing it forward.
@aiatmeta
-
Voicebox Outperforms Specialized AI Models with In-Context Learning
By
–
Voicebox generalizes across tasks and outperforms single-purpose AI models through in-context learning. It beats the previous state of the art in a number of ways. Better word error rates Improved audio similarity Up to 20x faster performance
-
Voicebox: Generative AI for High-Quality Audio Creation and Editing
By
–
Like other generative AI work, Voicebox is able to create high-quality outputs from scratch or modify samples, but instead of images/video, it produces high-quality audio. Unlike autoregressive models, it can modify any part of a given sample — not just the end of a clip.
-
Meta AI Introduces Voicebox Generative Speech System
By
–
Introducing Voicebox, a new breakthrough generative speech system based on Flow Matching, a new method proposed by Meta AI. It can synthesize speech across six languages, perform noise removal, edit content, transfer audio style & more. More details on this work & examples
-
EnCodec Code Released on GitHub Under MIT License
By
–
The code is available on GitHub for you to build on, released under the MIT license https://
github.com/facebookresear
ch/encodec
… -
Research SuperCluster Enables Breakthrough AI Research at Scale
By
–
The Research SuperCluster enables our research teams to do new, breakthrough AI research at an even greater scale and pace than ever before. Ning Dong and Maha Elbayad shared more about how it's enabling their work.
— AI at Meta (@AIatMeta) 15 juin 2023
More details ➡️ https://t.co/i1W6ld96Eb pic.twitter.com/ZgtcmrzF8OThe Research SuperCluster enables our research teams to do new, breakthrough AI research at an even greater scale and pace than ever before. Ning Dong and Maha Elbayad shared more about how it's enabling their work. More details https://
bit.ly/3N2qHCR -
Open-Sourcing Research Work for CVPR 2023 Conference
By
–
In support of open science and the research community, we're open-sourcing this work — and we'll be presenting it at #CVPR2023 next week. Training code and model checkpoints
-
I-JEPA Delivers Strong Computer Vision Performance with Efficiency
By
–
The approach taken with I-JEPA delivers strong performance across a number of computer vision tasks and does so with greater computational efficiency compared to other widely used computer vision models.
-
I-JEPA: Self-Supervised Computer Vision Learning Through Prediction
By
–
Today we're releasing our work on I-JEPA — self-supervised computer vision that learns to understand the world by predicting it. It's the first model based on a component of @ylecun
's vision to make AI systems learn and reason like animals and humans. Details -
Meta Scales Speech Technology to 1,100+ Languages Globally
By
–
Our work on the Massively Multilingual Speech (MMS) project has scaled speech-to-text & text-to-speech to support 1,100+ languages + trained new language identification models that can identify 4,000+ languages!
— AI at Meta (@AIatMeta) 12 juin 2023
More info & access to pretrained models ⬇️Our work on the Massively Multilingual Speech (MMS) project has scaled speech-to-text & text-to-speech to support 1,100+ languages + trained new language identification models that can identify 4,000+ languages! More info & access to pretrained models