Microsoft

Measure Audio Quality (DNSMOS)

Scores each AudioFrame with the DNSMOS network and emits four MOS-style quality numbers (speech, background, overall, and a P.808 estimate), shaped either as a named record or a [Analytics.Metric] list depending on what the downstream stage expects.

Extract Text (Florence 2)

Transcribes text in each Image with Microsoft Florence-2, emitting either a plain String transcript or per-region records with a Polygon quad or Rectangle box and the recognised text.

Segment Referring Expression (Florence 2)

Referring-expression segmentation with Florence-2: takes an Image and a String phrase naming one object, and emits the referent's contours as [Polygon], rasterised [Mask], or [Segmentation], resolved by the sink.

Detect Objects Open Vocabulary (Florence 2)

Localizes whatever a per-message String query phrase names within an Image via Florence-2 open-vocabulary detection, projecting the detections onto the connected output shape: boxes, geometry, classes, a count, or an overlay. Offline from the bound model.

Extract Text (TrOCR)

Recognises the text in a single cropped Image line with a TrOCR vision encoder-decoder and emits either a bare String transcript or a {text: String, confidence: Double} record pairing the transcript with the mean per-token recogniser score.

Ground Phrase (Florence 2)

Localises the noun phrases of a caption in an image: it runs Florence-2 phrase grounding over an Image and a String, emitting either bare [Rectangle] boxes or labelled [{bounds, label}] regions depending on how the output is wired.

Describe Image Regions (Florence 2)

Florence-2 dense region captioning: takes an Image, proposes regions, and emits [{bounds: Rectangle, caption: String}] — one short free-text caption per region, in pixel space, with no class id or confidence.

Detect Objects (Florence 2)

Runs Florence-2 closed-set detection over each Image, emitting the shape the connected output picks: [BoundingBox], [Rectangle], [DetectedClass], a UInt64 count, or an Image overlay. Offline from the bound model.

Extract Tables TATR

Detects table structure in a document Image with Microsoft Table Transformer and emits either [Rectangle] geometry boxes or [BoundingBox] with class ids, filtered by score_threshold. Use for table layout extraction from pages.