Audio recording directly from the browser and audio file upload support (Whisper API: .mp3, .mp4, .mpeg, .mpga , .m4a, and .wav) Conversion of transcribed text to Mermaid.js diagram code Live editing ...

To optimize training, the researchers first trained only the encoder on text ... in diagram recognition. From complex chemical structural formulas to musical notation and data visualization: OCR 2.0 ...