danielrosehill/hebrew-latin-token-classifier
Finds Hebrew words written in Latin letters inside English text (span F1 0.941). XLM-R base token classifier, built for routing Hebrew spans to a Hebrew TTS voice.
Run danielrosehill/hebrew-latin-token-classifier with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
Input schema
The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| text |
string
|
English text that may contain Hebrew words in Latin letters.
|
|
| threshold |
number
|
0.5
Max: 1 |
Minimum P(Hebrew) for a word. Raise it for fewer false positives (TTS).
|
{
"type": "object",
"title": "Input",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"title": "Text",
"x-order": 0,
"description": "English text that may contain Hebrew words in Latin letters."
},
"threshold": {
"type": "number",
"title": "Threshold",
"default": 0.5,
"maximum": 1,
"minimum": 0,
"x-order": 1,
"description": "Minimum P(Hebrew) for a word. Raise it for fewer false positives (TTS)."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "array",
"items": {
"type": "object"
},
"title": "Output"
}