Initial version: English-Russian translator app

README.md

@@ -10,4 +10,41 @@ pinned: false
 license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# English-to-Russian Translator
+
+A simple web application for translating text from English to Russian using a pre-trained neural model.
+
+## Features
+- Web interface built with [Gradio](https://gradio.app/)
+- Uses the Hugging Face model [`Helsinki-NLP/opus-mt-en-ru`](https://huggingface.co/Helsinki-NLP/opus-mt-en-ru) for translation
+- Input field for English text, translation button, and output field for Russian translation
+- Handles empty input and long text errors gracefully
+
+## How to Run (Locally)
+1. Установите зависимости:
+    ```bash
+    pip install -r requirements.txt
+    ```
+2. Запустите приложение:
+    ```bash
+    python app.py
+    ```
+3. Откройте браузер и перейдите по адресу http://127.0.0.1:7860
+
+## How to Deploy on Hugging Face Spaces
+1. Загрузите в репозиторий следующие файлы:
+    - `app.py`
+    - `requirements.txt`
+    - `README.md`
+2. Создайте новый Space на [Hugging Face Spaces](https://huggingface.co/spaces) с типом Gradio.
+3. После загрузки файлов приложение автоматически соберётся и будет доступно онлайн.
+
+---
+
+## About
+- This project was created in the **Windsurf** environment with the help of GPT-4.1.
+- Author: [Trashchenkov Sergei](https://github.com/trashchenkov)
+
+
+
+**Made with ❤️ using Gradio, Hugging Face Transformers, and GPT-4.1 in Windsurf.**

app.py

@@ -0,0 +1,36 @@
+import gradio as gr
+from transformers import MarianMTModel, MarianTokenizer
+import torch
+
+# Загрузка модели и токенизатора
+MODEL_NAME = "Helsinki-NLP/opus-mt-en-ru"
+tokenizer = MarianTokenizer.from_pretrained(MODEL_NAME)
+model = MarianMTModel.from_pretrained(MODEL_NAME)
+
+def translate(text):
+    if not text.strip():
+        return "Пожалуйста, введите текст для перевода."
+    if len(text) > 500:
+        return "Слишком длинный текст. Пожалуйста, введите до 500 символов."
+    try:
+        batch = tokenizer([text], return_tensors="pt", padding=True)
+        with torch.no_grad():
+            gen = model.generate(**batch)
+        translated = tokenizer.batch_decode(gen, skip_special_tokens=True)[0]
+        return translated
+    except Exception as e:
+        return f"Ошибка при переводе: {str(e)}"
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Переводчик с английского на русский")
+    with gr.Row():
+        input_text = gr.Textbox(label="Текст на английском", placeholder="Введите текст на английском языке")
+    with gr.Row():
+        translate_btn = gr.Button("Перевести")
+    with gr.Row():
+        output_text = gr.Textbox(label="Перевод на русский", interactive=False)
+
+    translate_btn.click(translate, inputs=input_text, outputs=output_text)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+gradio>=3.0.0
+transformers>=4.0.0
+torch
+sentencepiece