An hour of audio transcribed in about 13s on MacBook Air

Automated excerpt

Google's EmbeddingGemma 2 is an embedding model. EmbeddingGemma 2 is a multimodal embedding model: text, images, audio and video in one shared space. The base model was never trained for speech-to-text.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.