Spaces:

burask
/

transcript

Sleeping

App Files Files Community

burask commited on Aug 12

Commit

7a7248b

verified ·

1 Parent(s): 4c80c5f

Upload 4 files

Browse files

Files changed (4) hide show

Dockerfile +11 -0
app.py +82 -0
requirements.txt +0 -0
templates/index.html +119 -0

Dockerfile ADDED Viewed

	@@ -0,0 +1,11 @@

+FROM python:3.10
+RUN apt-get update && apt-get install -y ffmpeg
+COPY requirements.txt /app/requirements.txt
+RUN pip install --no-cache-dir -r /app/requirements.txt
+COPY . /app
+WORKDIR /app
+CMD ["python", "app.py"]

app.py ADDED Viewed

	@@ -0,0 +1,82 @@

+from flask import Flask, render_template, request
+import os
+import subprocess
+from speech_recognition import Recognizer, AudioFile
+from werkzeug.utils import secure_filename
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from deepmultilingualpunctuation import PunctuationModel
+app = Flask(__name__)
+yuklenen_dosyalar = "uploads"
+app.config["yuklenen_dosyalar"] = yuklenen_dosyalar
+dosya_turleri = {"mp3", "m4a"}
+# Modelleri yükle
+tokenizer = AutoTokenizer.from_pretrained("csebuetnlp/mT5_multilingual_XLSum")
+model = AutoModelForSeq2SeqLM.from_pretrained("csebuetnlp/mT5_multilingual_XLSum")
+punct_model = PunctuationModel(model="oliverguhr/fullstop-punctuation-multilingual-sonar-base")
+def metin_duzenleme(text):
+    text = text.strip()
+    try:
+        return punct_model.restore_punctuation(text)
+    except Exception as e:
+        print("Noktalama hatası:", e)
+        return text
+def metin_ozetleme(text):
+    girilen_metin = "tr: " + text
+    girilenler = tokenizer([girilen_metin], return_tensors="pt", max_length=10000, truncation=True)
+    summary_ids = model.generate(
+        girilenler["input_ids"],
+        max_length=1000,
+        min_length=1,
+        length_penalty=1.0,
+        num_beams=4,
+        early_stopping=True
+    )
+    return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+def uygun_turler(filename):
+    return "." in filename and filename.rsplit(".", 1)[1].lower() in dosya_turleri
+def convert_mp3_to_wav(mp3_path):
+    wav_path = mp3_path.rsplit('.', 1)[0] + '.wav'
+    subprocess.run(['ffmpeg', '-i', mp3_path, wav_path, '-y'], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
+    return wav_path
+def ses_donusturucu(wav_path):
+    recognizer = Recognizer()
+    with AudioFile(wav_path) as source:
+        ses = recognizer.record(source)
+    try:
+        return recognizer.recognize_google(ses, language="tr-TR")
+    except Exception as e:
+        return f"Ses tanıma hatası: {e}"
+@app.route("/", methods=["GET", "POST"])
+def index():
+    if request.method == "POST":
+        if "file" not in request.files:
+            return "Dosya bulunamadı."
+        file = request.files["file"]
+        if file.filename == "":
+            return "Dosya seçilmedi."
+        if file and uygun_turler(file.filename):
+            filename = secure_filename(file.filename)
+            file_path = os.path.join(app.config["yuklenen_dosyalar"], filename)
+            file.save(file_path)
+            wav_path = convert_mp3_to_wav(file_path)
+            raw_text = ses_donusturucu(wav_path)
+            metin = metin_duzenleme(raw_text)
+            ozet = metin_ozetleme(metin)
+            return render_template("index.html", metin=metin, ozet=ozet)
+    return render_template("index.html")
+if __name__ == "__main__":
+    if not os.path.exists(yuklenen_dosyalar):
+        os.makedirs(yuklenen_dosyalar)
+    port = int(os.environ.get("PORT", 7860))  # Hugging Face için 7860 port
+    app.run(host="0.0.0.0", port=port, debug=False)

requirements.txt ADDED Viewed

Binary file (204 Bytes). View file

templates/index.html ADDED Viewed

	@@ -0,0 +1,119 @@

+<!DOCTYPE html>
+<html lang="tr">
+<head>
+    <meta charset="UTF-8">
+    <title>🎙️Transkript</title>
+    <link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="stylesheet">
+    <style>
+        html, body {
+            margin: 0;
+            padding: 0;
+            height: 100%;
+            font-family: "cursive";
+            overflow: hidden;
+            display: flex;
+            justify-content: center;
+            align-items: center;
+        }
+        #particles-js {
+            position: fixed;
+            width: 100%;
+            height: 100%;
+            background-color: #0d1b2a;
+            z-index: -1;
+        }
+      .container {
+    max-width: 1000px;
+    width: 95%;
+    background: rgba(176, 26, 26, 0.459);
+    padding: 50px;
+    border-radius: 20px;
+    box-shadow: 0 0 30px rgba(255, 255, 255, 0.3);
+    z-index: 1;
+    color: #fff;
+}
+.output-box {
+    margin-top: 15px;
+    background: #e9ecef;
+    padding: 10px;
+    border-radius: 10px;
+    white-space: pre-wrap;
+    max-height: 300px;
+    overflow-y: auto;
+    color: #000;
+}
+.output-box h2,
+.output-box h3,
+.output-box p {
+    margin-top: 5px;
+    margin-bottom: 5px;
+}
+    </style>
+</head>
+<body>
+    <div id="particles-js"></div>
+    <div class="container">
+        <h2 class="text-center mb-4">🎙️ Ses Dosyasını Metne Dönüştür</h2>
+        <form method="POST" enctype="multipart/form-data">
+            <div class="mb-3">
+                <label for="file" class="form-label">Ses Dosyası Seç (.mp3)</label>
+                <input class="form-control" type="file" name="file" id="file" required>
+            </div>
+            <div class="d-grid">
+                <button type="submit" class="btn btn-primary btn-lg">Yükle ve Dönüştür</button>
+            </div>
+        </form>
+        {% if metin %}
+    <div class="output-box mt-1">
+        <h5>🎧 Dönüştürülen Metin:</h5>
+        <p>{{ metin }}</p>
+    </div>
+        {% if ozet %}
+        <div class="output-box mt-4">
+            <h5>📝 Metnin Özeti:</h5>
+            <p>{{ ozet }}</p>
+        </div>
+        {% endif %}
+          {% endif %}
+    </div>
+    <p style="position: fixed; bottom: 20px; left: 20px; color:#ffffff;">Designer by: Burak Tuğrul Aşık & Tarık Kahraman</p>
+    <script src="https://cdn.jsdelivr.net/npm/particles.js"></script>
+    <script>
+        particlesJS('particles-js', {
+            "particles": {
+                "number": { "value": 90, "density": { "enable": true, "value_area": 800 } },
+                "color": { "value": "#ffffff" },
+                "shape": { "type": "star", "stroke": { "width": 0, "color": "#ffffff" }, "polygon": { "nb_sides": 5 } },
+                "opacity": { "value": 0.5, "random": false },
+                "size": { "value": 3, "random": false },
+                "line_linked": { "enable": true, "distance": 150, "color": "#ffffff", "opacity": 0.4, "width": 1 },
+                "move": { "enable": true, "speed": 1, "direction": "none", "random": false, "straight": false, "out_mode": "out", "bounce": false }
+            },
+            "interactivity": {
+                "detect_on": "canvas",
+                "events": {
+                    "onhover": { "enable": true, "mode": "repulse" },
+                    "onclick": { "enable": true, "mode": "push" },
+                    "resize": true
+                },
+                "modes": {
+                    "repulse": { "distance": 100, "duration": 0.4 },
+                    "push": { "particles_nb": 4 }
+                }
+            },
+            "retina_detect": true
+        });
+    </script>
+</body>
+</html>