Spaces:
Runtime error
Runtime error
File size: 3,583 Bytes
f698312 |
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 |
import gradio as gr
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForTokenClassification
import torch
import pandas as pd
# Load the models and tokenizers
QA_model = AutoModelForQuestionAnswering.from_pretrained("guldasta/xtreme-MLQA.hi.hi")
QA_token = AutoTokenizer.from_pretrained("guldasta/xtreme-MLQA.hi.hi")
Translation_model = AutoModelForSeq2SeqLM.from_pretrained("guldasta/Helsinki-NLP-opus-mt-mul-en-finetuned-hi-to-en")
Translation_token = AutoTokenizer.from_pretrained("guldasta/Helsinki-NLP-opus-mt-mul-en-finetuned-hi-to-en")
TokenClass_Model = AutoModelForTokenClassification.from_pretrained("guldasta/roberta-ner-multilingua-HiNER-Org")
TokenClass_Token = AutoTokenizer.from_pretrained("guldasta/roberta-ner-multilingua-HiNER-Org")
# Define the functions
def get_ans(question, context):
model_inputs = QA_token(question, context, return_tensors="pt")
outputs = QA_model(**model_inputs)
start_logits = outputs.start_logits
end_logits = outputs.end_logits
start_indx = torch.argmax(start_logits)
end_indx = torch.argmax(end_logits)
answer = QA_token.decode(model_inputs['input_ids'][0][start_indx:end_indx + 1])
return answer
def translate_text(text):
model_inputs = Translation_token(text, return_tensors="pt")
outputs = Translation_model.generate(**model_inputs)
translated_text = Translation_token.decode(outputs[0], skip_special_tokens=True)
return translated_text
def get_pos(text):
inputs = TokenClass_Token(text, return_tensors="pt")
outputs = TokenClass_Model(**inputs)
logits = outputs.logits
predictions = torch.argmax(logits, dim=2)
tokens = TokenClass_Token.convert_ids_to_tokens(inputs["input_ids"][0])
predicted_labels = [TokenClass_Model.config.id2label[label.item()] for label in predictions[0]]
filtered_tokens = []
filtered_labels = []
for token, label in zip(tokens, predicted_labels):
if token not in TokenClass_Token.all_special_tokens:
filtered_tokens.append(token)
filtered_labels.append(label)
df = pd.DataFrame({
"Token": filtered_tokens,
"Entity": filtered_labels
})
return df
# Create Gradio interfaces
qa_interface = gr.Interface(
fn=get_ans,
inputs=[
gr.Textbox(lines=5, placeholder="Type a paragraph or context here...", label="Paragraph"),
gr.Textbox(lines=1, placeholder="Type your question here...", label="Question"),
],
outputs=gr.Textbox(label="Answer"),
title="Question Answering",
description="Enter a paragraph and ask a question to get the answer."
)
translation_interface = gr.Interface(
fn=translate_text,
inputs=gr.Textbox(lines=2, placeholder="Type your text here...", label="Text to Translate"),
outputs=gr.Textbox(label="Translated Text"),
title="Text Translation",
description="Enter text to translate from Hindi to English."
)
pos_tag_interface = gr.Interface(
fn=get_pos,
inputs=gr.Textbox(lines=2, placeholder="Type your text here...", label="Text for POS Tagging"),
outputs=gr.Dataframe(headers=["Token", "Entity"]),
title="POS Tagging",
description="Enter text to get POS tags and named entities."
)
# Combine all interfaces into a single Gradio app
app = gr.TabbedInterface(
[qa_interface, translation_interface, pos_tag_interface],
["Question Answering", "Translation", "POS Tagging"]
)
# Launch the app
app.launch()
|