Upload folder using huggingface_hub

app.py

@@ -0,0 +1,118 @@
+'''
+        Created By Lewis Kamau Kimaru 
+        Sema fastapi backend
+        August 2023
+'''
+
+from fastapi import FastAPI, HTTPException, Request
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import HTMLResponse
+from flores200_codes import flores_codes
+import gradio as gr
+import ctranslate2
+import sentencepiece as spm
+import fasttext
+import uvicorn
+from pyngrok import ngrok
+import nest_asyncio
+import os
+
+app = FastAPI()
+
+# Set your ngrok authtoken
+#ngrok.set_auth_token("2UAhCqf5zP0cCgJzeadNANkbIqx_7ZJvhkDSNWccqMX2hyxXP")
+#ngrok.set_auth_token("2S6xeFEoSVFWr2egtDRcqgeUtSx_2juefHFkEW6nGbpRHS37W")
+#ngrok.set_auth_token("2UAmdjHdAFV9x84TdyEknIfNhYk_4Ye8n4YK7ZhfCMob3yPBh")
+#ngrok.set_auth_token("2UAqm26HuWiWvQjzK58xYufSGpy_6tStKSyLLyR9f7pcezh6R")
+ngrok.set_auth_token("2UGQqzZoI3bx7SSk8H4wuFC3iaC_2WniWyNAsW5fd2rFyKVq1")
+
+
+fasttext.FastText.eprint = lambda x: None
+
+# Load the model and tokenizer ..... only once!
+beam_size = 1  # change to a smaller value for faster inference
+device = "cpu"  # or "cuda"
+
+# Language Prediction model
+print("\nimporting Language Prediction model")
+lang_model_file = "Sema/lid218e.bin"
+lang_model_full_path = os.path.join(os.path.dirname(__file__), lang_model_file)
+lang_model = fasttext.load_model(lang_model_full_path)
+
+
+# Load the source SentencePiece model
+print("\nimporting SentencePiece model")
+sp_model_file = "Sema/spm.model"
+sp_model_full_path = os.path.join(os.path.dirname(__file__), sp_model_file)
+sp = spm.SentencePieceProcessor()
+sp.load(sp_model_full_path)
+
+# Import The Translator model
+print("\nimporting Translator model")
+ct_model_file = "Sema/sematrans-3.3B"
+ct_model_full_path = os.path.join(os.path.dirname(__file__), ct_model_file)
+translator = ctranslate2.Translator(ct_model_full_path, device)
+
+print('\nDone importing models\n')
+
+    
+def translate_text(userinput: str, target_lang: str):
+    source_sents = [userinput]
+    source_sents = [sent.strip() for sent in source_sents]
+    target_prefix = [[target_lang]] * len(source_sents)
+
+    # Predict the source language
+    predictions = lang_model.predict(source_sents[0], k=1)
+    source_lang = predictions[0][0].replace('__label__', '')
+
+    # Subword the source sentences
+    source_sents_subworded = sp.encode(source_sents, out_type=str)
+    source_sents_subworded = [[source_lang] + sent + ["</s>"] for sent in source_sents_subworded]
+
+    # Translate the source sentences
+    translations = translator.translate_batch(
+        source_sents_subworded,
+        batch_type="tokens",
+        max_batch_size=2024,
+        beam_size=beam_size,
+        target_prefix=target_prefix,
+    )
+    translations = [translation[0]['tokens'] for translation in translations]
+
+    # Desubword the target sentences
+    translations_desubword = sp.decode(translations)
+    translations_desubword = [sent[len(target_lang):] for sent in translations_desubword]
+
+    # Return the source language and the translated text
+    return source_lang, translations_desubword
+
+
+@app.get("/")
+def read_root():
+    return {"message": "Welcome to the Sema Translation API! \nThis API was created by Lewsi Kamau Kimaru"}
+
+
+@app.post("/translate/")
+async def translate_endpoint(request: Request):
+    data = await request.json()
+    userinput = data.get("userinput")
+    target_lang = data.get("target_lang")
+    print(f"\n Target Language; {target_lang}, User Input: {userinput}\n")
+
+    if not userinput or not target_lang:
+        raise HTTPException(status_code=422, detail="Both 'userinput' and 'target_lang' are required.")
+
+    source_lang, translated_text = translate_text(userinput, target_lang)
+    print(f"\nsource_language: {source_lang}, Translated Text: {translated_text}\n\n")
+    return {
+        "source_language": source_lang,
+        "translated_text": translated_text[0],
+    }
+
+ngrok_tunnel = ngrok.connect(7860)
+public_url = ngrok_tunnel.public_url
+print('\nPublic URL✅:', public_url)
+nest_asyncio.apply()
+
+print("\nAPI starting .......\n")
+uvicorn.run(app, port=7860)

index.html

@@ -0,0 +1,52 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width">
+    <title>Sema Translator</title>
+    <link rel="stylesheet" href="style.css" />
+    <py-script src="modules/app.py"></py-script>
+</head>
+<body>
+    <div class="Header">
+        <h1>Sema Translator</h1>
+        <p>Unlock the Power of Global Communication with Sema Translator! Seamlessly bridging language barriers. With support for over 200 languages, Sema Translator opens up a realm of possibilities for building truly global applications.</p>
+        
+    </div>
+    
+    <div class="LanguageDropdown">
+        <h2>Select a Language:</h2>
+        <select id="languageSelect">
+            <!-- Add options dynamically -->
+        </select>
+    </div>
+    
+    <div class="instructions">
+        <p>Use the following python code to access the api endpoint</p>
+        <pre style="text-align: left;">
+import requests
+
+url = "{public_url}/translate/"
+data = {
+    "userinput": "rũcinĩ rwega, niwokĩra wega?",
+    "target_lang": "eng_Latn",
+}
+
+response = requests.post(url, json=data)
+result = response.json()
+
+print(result)
+
+source_language = result['source_language']
+print("Source Language:", source_language)
+
+translation = result['translated_text']
+print("Translated text:", translation)
+        </pre>
+    </div>
+    
+    <div class="footer">
+        <h1>Created by Lewis Kamau Kiamru</h1>
+    </div>
+</body>
+</html>

style.css

@@ -0,0 +1,13 @@
+        .Header {
+            text-align: center;
+        }
+        .LanguageDropdown {
+            text-align: center;
+        }
+        .instructions {
+            background-color: #056e33;
+            padding: 20px;
+        }
+        .footer {
+            text-align: center;
+        }