Skip to content
HALOWERK

Textwerk

hate speech de

Two open classifiers run locally (onnxruntime-node, pinned revisions, SHA-256 checked, downloaded once over hole()): Horizon-Labs/multilingual-hate-speech-base (Apache-2.0; mmBERT-base, MIT) for hate speech, i.e. attacks on people because of race/ethnicity, nationality/migration, religion, gender, sexual orientation, gender identity, disability or age, with seven target-group probabilities; and Horizon-Labs/multilingual-toxicity-small (Apache-2.0; trained on Civil Comments, CC0, and.

POST https://text.halowerk.com/v1/hate-speech-de

Inputs

Fields of the published input schema
FieldTypeRequiredDescription
textsarrayYesComments or posts, scored one by one (together at most 1,500 model tokens).
thresholdnumberNoFlag threshold for hate and insult.
Show full input schema
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "texts"
  ],
  "properties": {
    "texts": {
      "type": "array",
      "minItems": 1,
      "maxItems": 16,
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 4000
      },
      "description": "Comments or posts, scored one by one (together at most 1,500 model tokens)."
    },
    "threshold": {
      "type": "number",
      "minimum": 0.05,
      "maximum": 0.95,
      "default": 0.5,
      "description": "Flag threshold for hate and insult."
    }
  }
}

Open original schema

Published input example

{
  "texts": [
    "Die sind alle Ungeziefer, schmeißt sie raus.",
    "Du bist ein kompletter Vollidiot.",
    "Danke für den hilfreichen Beitrag!"
  ]
}

Result & documentation

Machine-readable documentation of this hub

Source of this page: the published HALOWERK catalog. Updated: 2026-11-17 UTC.

More endpoints in this hub

All endpoints in this hub →