Spaces:
Sleeping
Sleeping
| import os | |
| import streamlit as st | |
| from typing import List | |
| # Load Hugging Face Marian model (Helsinki-NLP) locally or via API | |
| def load_tokenizer_model(model_name: str): | |
| try: | |
| from transformers import MarianTokenizer, MarianMTModel | |
| except Exception: | |
| st.error("transformers library not installed. Run: pip install transformers sentencepiece") | |
| raise | |
| tokenizer = MarianTokenizer.from_pretrained(model_name) | |
| model = MarianMTModel.from_pretrained(model_name) | |
| return tokenizer, model | |
| def translate_local(texts: List[str], tokenizer, model) -> List[str]: | |
| batch = tokenizer(texts, return_tensors="pt", padding=True, truncation=True) | |
| generated = model.generate(**batch, max_length=512) | |
| return tokenizer.batch_decode(generated, skip_special_tokens=True) | |
| def translate_via_inference_api(text: str, model_name: str, hf_token: str) -> str: | |
| import requests | |
| API_URL = f"https://api-inference.huggingface.co/models/{model_name}" | |
| headers = {"Authorization": f"Bearer {hf_token}"} | |
| payload = {"inputs": text} | |
| res = requests.post(API_URL, headers=headers, json=payload, timeout=60) | |
| res.raise_for_status() | |
| data = res.json() | |
| if isinstance(data, dict) and data.get('error'): | |
| raise RuntimeError(data['error']) | |
| if isinstance(data, list) and len(data) > 0: | |
| return data[0].get('translation_text') or data[0].get('generated_text') or str(data[0]) | |
| return str(data) | |
| # ---------------- Streamlit UI ---------------- | |
| st.set_page_config(page_title="English → Urdu Translator", layout="centered") | |
| st.title("🇬🇧 ➜ 🇵🇰 English → Urdu Translator") | |
| st.write("Streamlit app that translates English text to Urdu using Hugging Face models.") | |
| model_name = st.text_input("Model name", value="Helsinki-NLP/opus-mt-en-ur") | |
| use_api = st.checkbox("Use Hugging Face Inference API instead of local model") | |
| hf_token_env = os.environ.get("HF_API_TOKEN", "") | |
| hf_token_input = st.text_input("Hugging Face API token (optional; required only for Inference API)", value=hf_token_env, type="password") | |
| text_in = st.text_area("Input English text", height=200) | |
| # Handle Streamlit version differences | |
| try: | |
| col1, col2 = st.columns([1, 1]) | |
| except AttributeError: | |
| col1, col2 = st.beta_columns([1, 1]) | |
| with col1: | |
| translate_btn = st.button("Translate") | |
| with col2: | |
| clear_btn = st.button("Clear") | |
| if clear_btn: | |
| st.rerun() | |
| if translate_btn: | |
| if not text_in.strip(): | |
| st.warning("Please enter some English text to translate.") | |
| else: | |
| with st.spinner("Translating..."): | |
| try: | |
| if use_api: | |
| hf_token = hf_token_input.strip() | |
| if not hf_token: | |
| st.error("Hugging Face API token required when using Inference API. Set as HF_API_TOKEN env var or paste it here.") | |
| else: | |
| result = translate_via_inference_api(text_in, model_name, hf_token) | |
| st.subheader("Urdu translation") | |
| st.write(result) | |
| else: | |
| tokenizer, model = load_tokenizer_model(model_name) | |
| outputs = translate_local([text_in], tokenizer, model) | |
| st.subheader("Urdu translation") | |
| st.write(outputs[0]) | |
| except Exception as e: | |
| st.error(f"Translation failed: {e}") | |
| st.markdown("---") | |
| st.write("**Notes:**") | |
| st.write("- Local model download may take some time on first run and requires internet.\n- To use the Hugging Face Inference API, enable the checkbox and provide your API token from https://huggingface.co/settings/tokens.\n- Install dependencies: `pip install streamlit transformers sentencepiece requests`.") | |
| st.caption("Built with ❤️ — modify freely for your needs.") |