Instructions to use frissonlabs/script-parser-gemma3-270m-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use frissonlabs/script-parser-gemma3-270m-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'frissonlabs/script-parser-gemma3-270m-ONNX');
Script Parser 360M (ONNX)
Fine-tuned SmolLM2-360M-Instruct for theatrical script parsing.
Converts raw script text into pipe-delimited D|CHARACTER|parenthetical|line and S|stage direction format.
Usage with transformers.js
import { AutoTokenizer, AutoModelForCausalLM } from "@huggingface/transformers";
const tokenizer = await AutoTokenizer.from_pretrained("frissonlabs/script-parser-360m-ONNX");
const model = await AutoModelForCausalLM.from_pretrained("frissonlabs/script-parser-360m-ONNX", {
dtype: "q4f16",
device: "wasm", // or "webgpu"
});
Input/Output Format
Input (raw script text):
JOHN. (Crossing to the window.) I can't believe you said that.
Mary. I didn't say anything!
(The phone rings.)
Output (pipe-delimited):
D|JOHN|Crossing to the window.|I can't believe you said that.
D|MARY||I didn't say anything!
S|The phone rings.
- Downloads last month
- 6