Wav2Vec 2.0
Wav2Vec learns from sound by guessing missing parts of audio.
What it does
Wav2Vec learns from sound by guessing missing parts of audio.
Self-Supervised: Learning without human labels • Waveform: Sound shape
How it works
- Listen to lots of audio.
- Hide small parts of the sound.
- Learn by trying to guess the hidden parts.
Uses & Applications
- A speech tool can learn from audio without every second being typed by a person.
- A caption system can improve with more sound examples.
- A voice app can get better at different accents.
In short
It learns language from audio without needing many labels.
Try it yourself
Guess the hidden sound clue
One moment of a sound is hidden. The computer uses the moments on either side to guess what kind it was.
Your turn
Change one setting at a time. Reset example puts everything back.
Predict a masked audio segment
Step 1Why this happens