Spaces:
Running
Running
File size: 2,131 Bytes
b1c2932 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
import gradio as gr
import os
import torch
import numpy as np
from transformers import AutoModelForSequenceClassification
from transformers import AutoTokenizer
from huggingface_hub import HfApi
from label_dicts import MANIFESTO_LABEL_NAMES
HF_TOKEN = os.environ["hf_read"]
languages = [
"armenian", "bulgarian", "croatian", "czech", "danish", "dutch", "english",
"estonian", "finnish", "french", "georgian", "german", "greek", "hebrew",
"hungarian", "icelandic", "italian", "japanese", "korean", "latvian",
"lithuanian", "norwegian", "polish", "portuguese", "romanian", "russian",
"serbian", "slovak", "slovenian", "spanish", "swedish", "turkish"
]
def build_huggingface_path(language: str):
return "poltextlab/xlm-roberta-large-manifesto"
def predict(text, model_id, tokenizer_id):
device = torch.device("cpu")
model = AutoModelForSequenceClassification.from_pretrained(model_id, token=HF_TOKEN)
tokenizer = AutoTokenizer.from_pretrained(tokenizer_id)
model.to(device)
inputs = tokenizer(text,
max_length=512,
truncation=True,
padding="do_not_pad",
return_tensors="pt").to(device)
model.eval()
with torch.no_grad():
logits = model(**inputs).logits
probs = torch.nn.functional.softmax(logits, dim=1).cpu().numpy().flatten()
output_pred = {f"[{model.config.id2label[i]}] {MANIFESTO_LABEL_NAMES[int(model.config.id2label[i])]}": probs[i] for i in np.argsort(probs)[::-1]}
output_info = f'<p style="text-align: center; display: block">Prediction was made using the <a href="https://huggingface.co/{model_id}">{model_id}</a> model.</p>'
return output_pred, output_info
def predict_cap(text, language):
model_id = build_huggingface_path(language)
tokenizer_id = "xlm-roberta-large"
return predict(text, model_id, tokenizer_id)
demo = gr.Interface(
fn=predict_cap,
inputs=[gr.Textbox(lines=6, label="Input"),
gr.Dropdown(languages, label="Language")],
outputs=[gr.Label(num_top_classes=5, label="Output"), gr.Markdown()]) |