Spaces:
Runtime error
Runtime error
File size: 4,105 Bytes
f657d03 71775e2 f657d03 71775e2 f657d03 71775e2 f657d03 71775e2 f657d03 71775e2 f657d03 71775e2 f657d03 71775e2 f657d03 71775e2 f657d03 71775e2 f657d03 |
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 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 |
import datetime
import gradio as gr
from langdetect import detect, DetectorFactory, detect_langs
from transformers import pipeline
models = {'en': 'Narsil/deberta-large-mnli-zero-cls', # English
'de': 'Sahajtomar/German_Zeroshot', # German
'es': 'Recognai/zeroshot_selectra_medium', # Spanish
'it': 'joeddav/xlm-roberta-large-xnli', # Italian
'ru': 'DeepPavlov/xlm-roberta-large-en-ru-mnli', # Russian
'no': 'NbAiLab/nb-bert-base-mnli'} # Norsk
hypothesis_templates = {'en': 'This example is {}.', # English
'de': 'Dieses beispiel ist {}.', # German
'es': 'Este ejemplo es {}.', # Spanish
'it': 'Questo esempio è {}.', # Italian
'ru': 'Этот пример {}.', # Russian
'no': 'Dette eksempelet er {}.'} # Norsk
def detect_lang(sequence, labels):
DetectorFactory.seed = 0
seq_lang = 'en'
try:
seq_lang = detect(sequence)
lbl_lang = detect(labels)
except:
print("Language detection failed!",
"Date:{}, Sequence:{}, Labels:{}".format(
str(datetime.datetime.now()),
labels))
if seq_lang != lbl_lang:
print("Different languages detected for sequence and labels!",
"Date:{}, Sequence:{}, Labels:{}, Sequence Language:{}, Label Language:{}".format(
str(datetime.datetime.now()),
sequence,
labels,
seq_lang,
lbl_lang))
if seq_lang in models:
print("Sequence Language detected:",
"Date:{}, Sequence:{}, Sequence Language:{}".format(
str(datetime.datetime.now()),
sequence,
labels))
else:
print("Language not supported. Defaulting to English!",
"Date:{}, Sequence:{}, Sequence Language:{}".format(
str(datetime.datetime.now()),
sequence,
seq_lang))
seq_lang = 'en'
return seq_lang
def sequence_to_classify(sequence, labels):
label_clean = str(labels).split(",")
lang = detect_lang(sequence, labels)
classifier = pipeline("zero-shot-classification",
#hypothesis_template=hypothesis_templates[lang],
model=models[lang])
response = classifier(sequence, label_clean, multi_class=True)
predicted_labels = response['labels']
predicted_scores = response['scores']
clean_output = {idx: float(predicted_scores.pop(0)) for idx in predicted_labels}
print("Date:{}, Sequence:{}, Labels: {}".format(
str(datetime.datetime.now()),
sequence,
predicted_labels))
return clean_output
example_text1="Folkehelseinstituttets mest optimistiske anslag er at alle voksne er ferdigvaksinert innen midten av september."
example_labels1="politikk,helse,sport,religion"
example_text2="Kutt smør i terninger, og la det temperere seg litt mens deigen elter. Ha hvetemel, sukker, gjær, salt og kardemomme i en bakebolle til kjøkkenmaskin. Bruker du fersk gjær kan du smuldre gjæren i bollen, eller røre den ut i melken. Alt vil ettehvert blande seg godt, så begge deler er like bra."
example_labels2="helse,sport,religion, mat"
iface = gr.Interface(
title="Multilingual Multi-label Zero-shot Classification",
description="Currently supported languages are English, German, Spanish, Italian, Russian, Norsk.",
fn=sequence_to_classify,
inputs=[gr.inputs.Textbox(lines=20,
label="Please enter the text you would like to classify...",
placeholder="Text here..."),
gr.inputs.Textbox(lines=5,
label="Possible candidate labels (separated by comma)...",
placeholder="laLels here...")],
outputs=gr.outputs.Label(num_top_classes=5),
capture_session=True,
#interpretation="default",
examples=[
[example_text1, example_labels1],
[example_text2, example_labels2]
])
iface.launch()
|