Speech recognition

Community, Computer vision, Games, Human feedback, Image generation, Language, Open source, Reasoning, Reinforcement learning, Representation learning, Research, Responsible AI, Safety & Alignment, Speech recognition, Transformers, Video generation

Learning to play Minecraft with Video PreTraining

We trained a neural network to play Minecraft by Video PreTraining (VPT) on a massive unlabeled video dataset of human Minecraft play, while using only

Community, Computer vision, Human feedback, Image generation, Language, Open source, Reasoning, Reinforcement learning, Research, Responsible AI, Safety & Alignment, Speech recognition, Transformers, Video generation

DALL·E 2 pre-training mitigations

In order to share the magic of DALL·E 2 with a broad audience, we needed to reduce the risks associated with powerful image generation models.

Community, Computer vision, Human feedback, Language, Open source, Reasoning, Reinforcement learning, Research, Responsible AI, Safety & Alignment, Speech recognition, Transformers, Video generation

Efficient training of language models to fill in the middle

Community, Computer vision, Human feedback, Language, Open source, Reasoning, Reinforcement learning, Research, Responsible AI, Safety & Alignment, Speech recognition, Transformers, Video generation

A hazard analysis framework for code synthesis large language models

Community, Computer vision, Human feedback, Language, Open source, Reasoning, Reinforcement learning, Research, Responsible AI, Safety & Alignment, Speech recognition, Transformers, Video generation

Introducing Whisper

We’ve trained and are open-sourcing a neural net called Whisper that approaches human level robustness and accuracy on English speech recognition.