Official code for Wav2Seq

Robust Speech Recognition via Large-Scale Weak Supervision

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.