|
"""Gradio app to showcase the language detector.""" |
|
|
|
import gradio as gr |
|
from transformers import pipeline |
|
|
|
|
|
|
|
model_ckpt = "papluca/xlm-roberta-base-language-detection" |
|
pipe = pipeline("text-classification", model=model_ckpt) |
|
|
|
|
|
def predict(text: str) -> dict: |
|
"""Compute predictions for text.""" |
|
preds = pipe(text, return_all_scores=True, truncation=True, max_length=128) |
|
if preds: |
|
pred = preds[0] |
|
return {p["label"]: float(p["score"]) for p in pred} |
|
else: |
|
return None |
|
|
|
|
|
title = "Language detection with XLM-RoBERTa" |
|
description = "Determine the language in which your text is written." |
|
examples = [ |
|
["Better late than never."], |
|
["Tutto è bene ciò che finisce bene."], |
|
["Donde hay humo, hay fuego."], |
|
] |
|
explanation = "Supported languages are (20): arabic (ar), bulgarian (bg), german (de), modern greek (el), english (en), spanish (es), french (fr), hindi (hi), italian (it), japanese (ja), dutch (nl), polish (pl), portuguese (pt), russian (ru), swahili (sw), thai (th), turkish (tr), urdu (ur), vietnamese (vi), and chinese (zh)." |
|
|
|
app = gr.Interface( |
|
fn=predict, |
|
inputs=gr.inputs.Textbox( |
|
placeholder="What's the text you want to know the language for?", |
|
label="Text", |
|
lines=3, |
|
), |
|
outputs=gr.outputs.Label(num_top_classes=3, label="Your text is written in "), |
|
title=title, |
|
description=description, |
|
examples=examples, |
|
article=explanation, |
|
) |
|
|
|
app.launch() |
|
|
