Spaces:
Sleeping
Sleeping
File size: 2,485 Bytes
56b3258 17cebb5 56b3258 61e2291 56b3258 61e2291 56b3258 61e2291 56b3258 61e2291 56b3258 61e2291 56b3258 61e2291 56b3258 6113569 |
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 56 57 58 59 60 61 62 63 64 65 66 67 |
from transformers import pipeline
import gradio as gr
# Cargar modelos
model1 = "gyr66/RoBERTa-ext-large-crf-chinese-finetuned-ner-v2"
model2 = "gyr66/Ernie-3.0-large-chinese-finetuned-ner"
model3 = "gyr66/Ernie-3.0-base-chinese-finetuned-ner"
get_completion1 = pipeline("ner", model1)
get_completion2 = pipeline("ner", model2)
get_completion3 = pipeline("ner", model3)
# Funci贸n para fusionar tokens
def merge_tokens(tokens):
merged_tokens = []
for token in tokens:
if merged_tokens and token['entity'].startswith('I-') and merged_tokens[-1]['entity'].endswith(token['entity'][2:]):
# Si el token contin煤a la entidad del anterior, fusi贸nalos
last_token = merged_tokens[-1]
last_token['word'] += token['word'].replace('##', '')
last_token['end'] = token['end']
last_token['score'] = (last_token['score'] + token['score']) / 2
else:
# De lo contrario, agrega el token a la lista
merged_tokens.append(token)
return merged_tokens
# Funci贸n de NER
def ner(input):
output1 = get_completion1(input)
output2 = get_completion2(input)
output3 = get_completion3(input)
merged_tokens1 = merge_tokens(output1)
merged_tokens2 = merge_tokens(output2)
merged_tokens3 = merge_tokens(output3)
# Formatear la salida para Gradio
entities1 = [{"entity": t['entity'], "start": t['start'], "end": t['end']} for t in merged_tokens1]
entities2 = [{"entity": t['entity'], "start": t['start'], "end": t['end']} for t in merged_tokens2]
entities3 = [{"entity": t['entity'], "start": t['start'], "end": t['end']} for t in merged_tokens3]
return (
{"text": input, "entities": entities1},
{"text": input, "entities": entities2},
{"text": input, "entities": entities3}
)
# Crear interfaz Gradio
demo = gr.Interface(
fn=ner,
inputs=gr.Textbox(label="Text to find entities", lines=2),
outputs=[
gr.HighlightedText(label=f"NER Output - Model 1"),
gr.HighlightedText(label=f"NER Output - Model 2"),
gr.HighlightedText(label=f"NER Output - Model 3")
],
title="NER with Multiple Models",
description="Extract entities using three different models.",
allow_flagging="never",
examples=[
"My name is Andrew, I'm building DeeplearningAI and I live in California",
"My name is Poli, I live in Vienna and work at HuggingFace"
]
)
demo.launch(inline=False) |