Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import pandas as pd | |
| import requests | |
| from transformers import MarianMTModel, MarianTokenizer | |
| import io | |
| def fetch_languages(url): | |
| response = requests.get(url) | |
| if response.status_code == 200: | |
| # Convert bytes to a string using decode, then create a file-like object with io.StringIO | |
| csv_content = response.content.decode('utf-8') | |
| df = pd.read_csv(io.StringIO(csv_content), 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() | |
| language_options = [(row['ISO 639-1'], f"{row['ISO 639-1']} - {row['Language Name']}") for index, row in df.iterrows()] | |
| return language_options | |
| else: | |
| return [] | |
| # Make sure to replace the URL with the correct one if it has changed | |
| url = "https://huggingface.co/Lenylvt/LanguageISO/resolve/main/iso.md" | |
| language_options = fetch_languages(url) | |
| # Streamlit UI components | |
| st.title("📜 Translator") | |
| st.write("We use model from [Language Technology Research Group at the University of Helsinki](https://huggingface.co/Helsinki-NLP). For API use please visit [this space](https://huggingface.co/spaces/Lenylvt/Translator-API). 🔴 All Language are not Available") | |
| source_language = st.selectbox("1️⃣ Select Source Language", options=language_options, format_func=lambda x: x[1]) | |
| target_language = st.selectbox("2️⃣ Select Target Language", options=language_options, format_func=lambda x: x[1]) | |
| text = st.text_area("✒️ Enter text to translate...", height=150) | |
| def translate_text(text, source_language_code, target_language_code): | |
| 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) | |
| 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 | |
| except Exception as e: | |
| return f"Failed to load model for {source_language_code} to {target_language_code}: {str(e)}" | |
| if st.button("📁 Translate"): | |
| source_language_code, _ = source_language | |
| target_language_code, _ = target_language | |
| translation = translate_text(text, source_language_code, target_language_code) | |
| st.text_area("⬇️ Translated Text", value=translation, height=150, key="translation_output") | |