init app

README.md

@@ -1,10 +1,10 @@
 ---
 title: Translator
-emoji: 🐠
-colorFrom: green
+emoji: 🗣️
+colorFrom: blue
 colorTo: pink
 sdk: streamlit
-app_file: app.py
+app_file: main.py
 pinned: false
 ---
 

available_models.py

@@ -0,0 +1,32 @@
+"""🗣️ Translator - Translate text from one language to another.
+
+MODELS list all available models.
+"""
+
+MODELS = {
+    "🇬🇧 English->🇬🇧 English": [0,],
+    "🇬🇧 English->🇫🇷 French": ["Helsinki-NLP/opus-mt-en-fr", "https://huggingface.co/Helsinki-NLP/opus-mt-en-fr"],
+    "🇬🇧 English->🇩🇪 German": ["Helsinki-NLP/opus-mt-en-de", "https://huggingface.co/Helsinki-NLP/opus-mt-en-de"],
+    "🇬🇧 English->🇪🇸 Spanish": ["Helsinki-NLP/opus-mt-en-es", "https://huggingface.co/Helsinki-NLP/opus-mt-en-es"],
+    "🇬🇧 English->🇷🇺 Russian": ["Helsinki-NLP/opus-mt-en-ru", "https://huggingface.co/Helsinki-NLP/opus-mt-en-ru"],
+    "🇫🇷 French->🇫🇷 French": 0,
+    "🇫🇷 French->🇬🇧 English": ["Helsinki-NLP/opus-mt-fr-en", "https://huggingface.co/Helsinki-NLP/opus-mt-fr-en"],
+    "🇫🇷 French->🇩🇪 German": ["Helsinki-NLP/opus-mt-fr-de", "https://huggingface.co/Helsinki-NLP/opus-mt-fr-de"],
+    "🇫🇷 French->🇪🇸 Spanish": ["Helsinki-NLP/opus-mt-fr-es", "https://huggingface.co/Helsinki-NLP/opus-mt-fr-es"],
+    "🇫🇷 French->🇷🇺 Russian": ["Helsinki-NLP/opus-mt-fr-ru", "https://huggingface.co/Helsinki-NLP/opus-mt-fr-ru"],
+    "🇪🇸 Spanish->🇪🇸 Spanish": 0,
+    "🇪🇸 Spanish->🇬🇧 English": ["Helsinki-NLP/opus-mt-es-en", "https://huggingface.co/Helsinki-NLP/opus-mt-es-en"],
+    "🇪🇸 Spanish->🇩🇪 German": ["Helsinki-NLP/opus-mt-es-de", "https://huggingface.co/Helsinki-NLP/opus-mt-es-de"],
+    "🇪🇸 Spanish->🇫🇷 French": ["Helsinki-NLP/opus-mt-es-fr", "https://huggingface.co/Helsinki-NLP/opus-mt-es-fr"],
+    "🇪🇸 Spanish->🇷🇺 Russian": ["Helsinki-NLP/opus-mt-es-ru", "https://huggingface.co/Helsinki-NLP/opus-mt-es-ru"],
+    "🇩🇪 German->🇩🇪 German": 0,
+    "🇩🇪 German->🇬🇧 English": ["Helsinki-NLP/opus-mt-de-en", "https://huggingface.co/Helsinki-NLP/opus-mt-de-en"],
+    "🇩🇪 German->🇪🇸 Spanish": ["Helsinki-NLP/opus-mt-de-es", "https://huggingface.co/Helsinki-NLP/opus-mt-de-es"],
+    "🇩🇪 German->🇫🇷 French": ["Helsinki-NLP/opus-mt-de-fr", "https://huggingface.co/Helsinki-NLP/opus-mt-de-fr"],
+    "🇩🇪 German->🇷🇺 Russian": None,
+    "🇷🇺 Russian->🇷🇺 Russian": 0,
+    "🇷🇺 Russian->🇬🇧 English": ["Helsinki-NLP/opus-mt-ru-en", "https://huggingface.co/Helsinki-NLP/opus-mt-ru-en"],
+    "🇷🇺 Russian->🇪🇸 Spanish": ["Helsinki-NLP/opus-mt-ru-es", "https://huggingface.co/Helsinki-NLP/opus-mt-ru-es"],
+    "🇷🇺 Russian->🇫🇷 French": ["Helsinki-NLP/opus-mt-ru-fr", "https://huggingface.co/Helsinki-NLP/opus-mt-ru-fr"],
+    "🇷🇺 Russian->🇩🇪 German": None,
+}

main.py

@@ -0,0 +1,88 @@
+import re
+import streamlit as st
+
+from transformers import pipeline
+from available_models import MODELS
+
+
+st.set_page_config(page_title="Translator", page_icon="🗣️")
+st.title("🗣️ Translator")
+st.markdown("""
+[![GitHub](https://img.shields.io/badge/-%23121011.svg?style=for-the-badge&logo=github&logoColor=white)](https://github.com/ChainYo)
+[![HuggingFace](https://img.shields.io/badge/-yellow.svg?style=for-the-badge&logo=data:image/svg+xml;base64,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)](https://huggingface.co/ChainYo)
+[![LinkedIn](https://img.shields.io/badge/-%230077B5.svg?style=for-the-badge&logo=linkedin&logoColor=white)](https://www.linkedin.com/in/thomas-chaigneau-dev/)
+[![Discord](https://img.shields.io/badge/Chainyo%233610-%237289DA.svg?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/)
+""")
+st.subheader("Translation made fast and easy.")
+
+with st.expander("❓ How does it work"):
+    st.markdown("""
+    **Translator** is a **simple tool** that allows you to **translate text** from one language to another.
+
+    **Translator** is powered by the [Transformers library](https://huggingface.co/transformers) and uses the 
+    [Helsinki-NLP](https://huggingface.co/Helsinki-NLP) models.
+
+    Choose the **source language** and the **target language** and the **text to translate**.
+
+    **Translator** will translate the text and **save the output in a text file**. It cuts the text following 
+    punctuation marks.
+
+    The output file content will also be displayed in the browser to help you to understand the translation and choose 
+    if you want to download it.
+
+    There is **no limit to the number of characters** that can be translated. 
+    The only limit is the time you are ready to wait! 🤗
+
+    *P.S. I have built this tool to help me to start writing blog posts in different languages. I am a French native speaker
+    and I will use it to translate my potential future blog posts in English.*
+
+    *P.P.S. I am an **AI developer** passionate about **machine learning** and **data science**. Reach me by clicking on
+    the socials badges above.*
+    """)
+
+lang1, lang2 = st.columns(2)
+lang1.selectbox(
+    "Source Language", ["🇬🇧 English", "🇫🇷 French", "🇩🇪 German", "🇪🇸 Spanish", "🇷🇺 Russian"], 
+    key="input_lang", index=1,
+)
+lang2.selectbox(
+    "Target Language", ["🇬🇧 English", "🇫🇷 French", "🇩🇪 German", "🇪🇸 Spanish", "🇷🇺 Russian"], 
+    key="output_lang", index=0,
+)
+
+selected_model = MODELS[f"{st.session_state['input_lang']}->{st.session_state['output_lang']}"]
+
+st.markdown(f"""
+**Selected model:** [{selected_model[0]}]({selected_model[1]})
+""")
+
+if selected_model[0] == None:
+    st.write("No model available for this pair.")
+elif selected_model[0] == 0:
+    st.write("No translation necessary.")
+else:
+    input_text = st.text_area("Enter text to translate:", height=400, key="input")
+    translate_text = st.button("Translate")
+
+    if translate_text:
+        with st.spinner(text="⚙️ Model loading..."):
+            task = pipeline(
+                "translation",
+                model=selected_model[0],
+                tokenizer=selected_model[0],
+            )
+
+        progress_bar = st.progress(0)
+        with st.spinner(text="🔄 Translating..."):
+            text_to_translate = re.split('(?<=[.!?]) +', input_text)
+            total_progress = len(text_to_translate)
+
+            for i, text in enumerate(text_to_translate):
+                translation = task(text)
+                text_to_translate[i] = translation[0]["translation_text"]
+                progress_bar.progress((i + 1) / total_progress)
+
+        st.success("🗣️ Translated!")
+        st.session_state["translation_count"] += 1
+        st.write(f"**Translation:** {' '.join(text_to_translate)}")
+        st.download_button("Download translated text", "\n".join(text_to_translate), "text/plain")

requirements.txt

@@ -0,0 +1 @@
+streamlit==1.3.1