Understanding text that appears on images in social media platforms is important not just for improving experiences such as the incorporation of text into screen readers for the visually impaired, but they also help keep the community safe by proactively identify inappropriate or harmful content in a way that pure object detection or NLP systems alone cannot. This talk describes the challenges behind building an industry-scale Optical Character Recognition (OCR) system at Facebook that processes over a billion images each day. Viswanath will cover the Deep Learning methods behind building models that perform text detection in arbitrary orientations with high-accuracy, and how simple convolutional models work extremely well for recognizing text in over 50 languages. A critical aspect of the work is scaling up these models for efficient server-side inference. He’ll dive into quantization methods to run neural networks with 8-bit integer weights and activations instead of 32-bit floating points, and the challenges involved in doing so.