Abstract: We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, ...
New project, esp-idf-lib, succeeded this project. We will NOT update this repository. All new issues and PRs will NOT be accepted here. If you find any issues, please visit the relevant component ...
Look at any Overwatch forum with a post that mentions Jetpack Cat in the title, and there's a high chance it's a complaint or full of grumpy comments. Sometimes, it's about her ridiculous supply of ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results