|
import gradio as gr |
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("padmajabfrl/Gender-Classification") |
|
model = AutoModelForSequenceClassification.from_pretrained("padmajabfrl/Gender-Classification") |
|
|
|
|
|
def predict_gender(name): |
|
inputs = tokenizer(name, return_tensors="pt") |
|
outputs = model(**inputs) |
|
predictions = outputs.logits.argmax(dim=-1) |
|
predicted_label = model.config.id2label[predictions.item()] |
|
return predicted_label |
|
|
|
|
|
with gr.Blocks() as demo: |
|
gr.Markdown("<h1 style='text-align: center;'>Kaleida Gender Prediction Transformer</h1>") |
|
gr.Markdown("<h3 style='text-align: center;'>Tops Infosolution 🤝 Kaleida</h3>") |
|
|
|
with gr.Row(): |
|
with gr.Column(): |
|
name_input = gr.Textbox(label="Enter a Name", placeholder="Type a name here...", lines=1) |
|
classify_button = gr.Button("Predict Gender") |
|
|
|
with gr.Column(): |
|
output_label = gr.Label(label="Predicted Gender") |
|
|
|
classify_button.click(predict_gender, inputs=name_input, outputs=output_label) |
|
|
|
|
|
demo.launch() |
|
|