Spaces:
Sleeping
Sleeping
File size: 2,134 Bytes
4bdcdda d60a3d5 a03a333 d60a3d5 4bdcdda d65424d 4bdcdda 0f9dc19 4bdcdda d65424d 2189552 d65424d e8aca1c d65424d 2189552 4bdcdda 2189552 d60a3d5 550812d 4bdcdda d60a3d5 2189552 d65424d |
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 |
import requests
import pandas as pd
import gradio as gr
from transformers import MarianMTModel, MarianTokenizer
# Fetch and parse language options from the provided URL
url = "https://huggingface.co/Lenylvt/LanguageISO/resolve/main/iso.md"
response = requests.get(url)
df = pd.read_csv(response.url, delimiter="|", skiprows=2, header=None).dropna(axis=1, how='all')
df.columns = ['ISO 639-1', 'ISO 639-2', 'Language Name', 'Native Name']
df['ISO 639-1'] = df['ISO 639-1'].str.strip()
# Prepare language options for the dropdown
language_options = [(row['ISO 639-1'], f"{row['ISO 639-1']} - {row['Language Name']}") for index, row in df.iterrows()]
def translate_text(text, source_language_code, target_language_code):
source_language_code = source_language.split(' - ')[0].strip()
target_language_code = target_language.split(' - ')[0].strip()
# Construct model name using ISO 639-1 codes
model_name = f"Helsinki-NLP/opus-mt-{source_language_code}-{target_language_code}"
if source_language_code == target_language_code:
return "Translation between the same languages is not supported."
try:
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
except Exception as e:
return f"Failed to load model for {source_language_code} to {target_language_code}: {str(e)}"
translated = model.generate(**tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512))
translated_text = tokenizer.decode(translated[0], skip_special_tokens=True)
return translated_text
source_language_dropdown = gr.Dropdown(choices=language_options, label="Source Language")
target_language_dropdown = gr.Dropdown(choices=language_options, label="Target Language")
iface = gr.Interface(
fn=translate_text,
inputs=[gr.Textbox(lines=2, placeholder="Enter text to translate..."), source_language_dropdown, target_language_dropdown],
outputs=gr.Textbox(),
title="Text Translator with Dynamic Language Options",
description="Select source and target languages to translate text."
)
iface.launch()
|