Initial Push

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+media/audio/sample-song.mp3 filter=lfs diff=lfs merge=lfs -text

core/asgi.py

@@ -0,0 +1,16 @@
+"""
+ASGI config for core project.
+
+It exposes the ASGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/6.0/howto/deployment/asgi/
+"""
+
+import os
+
+from django.core.asgi import get_asgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'core.settings')
+
+application = get_asgi_application()

core/settings.py

@@ -0,0 +1,128 @@
+"""
+Django settings for core project.
+
+Generated by 'django-admin startproject' using Django 6.0.4.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/6.0/topics/settings/
+
+For the full list of settings and their values, see
+https://docs.djangoproject.com/en/6.0/ref/settings/
+"""
+
+from pathlib import Path
+import os
+# Build paths inside the project like this: BASE_DIR / 'subdir'.
+BASE_DIR = Path(__file__).resolve().parent.parent
+
+
+# Quick-start development settings - unsuitable for production
+# See https://docs.djangoproject.com/en/6.0/howto/deployment/checklist/
+
+# SECURITY WARNING: keep the secret key used in production secret!
+SECRET_KEY = 'django-insecure-bpm=z9@@=29etqf8x)a_8_-a^9adja%!@bt)%0*!*$hewld4*t'
+
+# SECURITY WARNING: don't run with debug turned on in production!
+DEBUG = True
+
+ALLOWED_HOSTS = []
+
+
+# Application definition
+
+INSTALLED_APPS = [
+    'django.contrib.admin',
+    'django.contrib.auth',
+    'django.contrib.contenttypes',
+    'django.contrib.sessions',
+    'django.contrib.messages',
+    'django.contrib.staticfiles',
+    'transcriber'
+]
+
+MIDDLEWARE = [
+    'django.middleware.security.SecurityMiddleware',
+    'django.contrib.sessions.middleware.SessionMiddleware',
+    'django.middleware.common.CommonMiddleware',
+    'django.middleware.csrf.CsrfViewMiddleware',
+    'django.contrib.auth.middleware.AuthenticationMiddleware',
+    'django.contrib.messages.middleware.MessageMiddleware',
+    'django.middleware.clickjacking.XFrameOptionsMiddleware',
+]
+
+ROOT_URLCONF = 'core.urls'
+
+TEMPLATES = [
+    {
+        'BACKEND': 'django.template.backends.django.DjangoTemplates',
+        'DIRS': [os.path.join(BASE_DIR, 'templates')],
+        'APP_DIRS': True,
+        'OPTIONS': {
+            'context_processors': [
+                'django.template.context_processors.request',
+                'django.contrib.auth.context_processors.auth',
+                'django.contrib.messages.context_processors.messages',
+            ],
+        },
+    },
+]
+
+WSGI_APPLICATION = 'core.wsgi.application'
+
+
+# Database
+# https://docs.djangoproject.com/en/6.0/ref/settings/#databases
+
+DATABASES = {
+    'default': {
+        'ENGINE': 'django.db.backends.sqlite3',
+        'NAME': BASE_DIR / 'db.sqlite3',
+    }
+}
+
+
+# Password validation
+# https://docs.djangoproject.com/en/6.0/ref/settings/#auth-password-validators
+
+AUTH_PASSWORD_VALIDATORS = [
+    {
+        'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
+    },
+]
+
+
+# Internationalization
+# https://docs.djangoproject.com/en/6.0/topics/i18n/
+
+LANGUAGE_CODE = 'en-us'
+
+TIME_ZONE = 'UTC'
+
+USE_I18N = True
+
+USE_TZ = True
+
+
+# Static files (CSS, JavaScript, Images)
+# https://docs.djangoproject.com/en/6.0/howto/static-files/
+
+
+
+STATIC_URL = 'static/'
+STATICFILES_DIRS = [os.path.join(BASE_DIR, 'static')]
+STATIC_ROOT = os.path.join(BASE_DIR, 'staticfiles')
+
+# URL that handles the media served from MEDIA_ROOT
+MEDIA_URL = '/media/'
+
+# Absolute filesystem path to the directory that will hold user-uploaded files
+MEDIA_ROOT = os.path.join(BASE_DIR, 'media')

core/urls.py

@@ -0,0 +1,14 @@
+from django.contrib import admin
+from django.urls import path, include
+from django.conf import settings
+# Update this specific line below:
+from django.conf.urls.static import static 
+
+urlpatterns = [
+    path('admin/', admin.site.urls), # Note: corrected to .urls
+    path('', include('transcriber.urls')),
+] 
+
+# This allows Django to serve files from the media folder during development
+if settings.DEBUG:
+    urlpatterns += static(settings.MEDIA_URL, document_root=settings.MEDIA_ROOT)

core/wsgi.py

@@ -0,0 +1,16 @@
+"""
+WSGI config for core project.
+
+It exposes the WSGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/6.0/howto/deployment/wsgi/
+"""
+
+import os
+
+from django.core.wsgi import get_wsgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'core.settings')
+
+application = get_wsgi_application()

manage.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+"""Django's command-line utility for administrative tasks."""
+import os
+import sys
+
+
+def main():
+    """Run administrative tasks."""
+    os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'core.settings')
+    try:
+        from django.core.management import execute_from_command_line
+    except ImportError as exc:
+        raise ImportError(
+            "Couldn't import Django. Are you sure it's installed and "
+            "available on your PYTHONPATH environment variable? Did you "
+            "forget to activate a virtual environment?"
+        ) from exc
+    execute_from_command_line(sys.argv)
+
+
+if __name__ == '__main__':
+    main()

media/audio/sample-song.mp3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b20c34a22298d81eac0181f8956c60ea7b23a39782d161884e272fcc3713bbd
+size 360533

transcriber/admin.py

@@ -0,0 +1,5 @@
+from django.contrib import admin
+from .models import Transcription
+
+# Register your models here.
+admin.site.register(Transcription)

transcriber/apps.py

@@ -0,0 +1,5 @@
+from django.apps import AppConfig
+
+
+class TranscriberConfig(AppConfig):
+    name = 'transcriber'

transcriber/migrations/0001_initial.py

@@ -0,0 +1,23 @@
+# Generated by Django 6.0.4 on 2026-05-05 11:45
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='Transcription',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('audio_file', models.FileField(upload_to='audio/')),
+                ('transcript_text', models.TextField(blank=True)),
+                ('created_at', models.DateTimeField(auto_now_add=True)),
+            ],
+        ),
+    ]

transcriber/models.py

@@ -0,0 +1,7 @@
+from django.db import models
+
+
+class Transcription(models.Model):
+    audio_file = models.FileField(upload_to='audio/')
+    transcript_text = models.TextField(blank=True)
+    created_at = models.DateTimeField(auto_now_add=True)

transcriber/templates/result.html

@@ -0,0 +1,31 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>Transcription Result</title>
+    <script src="https://cdn.tailwindcss.com"></script>
+</head>
+<body class="bg-gradient-to-br from-gray-900 to-black min-h-screen p-10 text-white">
+
+    <div class="max-w-4xl mx-auto">
+        <div class="flex justify-between items-center mb-8">
+            <h2 class="text-2xl font-bold text-purple-400">Transcription Complete</h2>
+            <a href="/" class="text-sm text-gray-400 hover:text-white transition">← Upload another</a>
+        </div>
+
+        <div class="bg-white/5 border border-white/10 rounded-2xl p-8 shadow-xl">
+            <h3 class="text-xs font-semibold text-gray-500 uppercase tracking-widest mb-4">Output Text</h3>
+            <p class="text-lg leading-relaxed text-gray-200">
+                {{ transcription.transcript_text }}
+            </p>
+        </div>
+
+        <div class="mt-6 flex gap-4">
+            <button onclick="navigator.clipboard.writeText('{{ transcription.transcript_text|escapejs }}')" class="px-6 py-2 bg-white/10 hover:bg-white/20 rounded-lg text-sm transition">
+                Copy to Clipboard
+            </button>
+        </div>
+    </div>
+
+</body>
+</html>

transcriber/templates/upload.html

@@ -0,0 +1,96 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Audio Transcriber</title>
+    <script src="https://cdn.tailwindcss.com"></script>
+</head>
+<body class="bg-gradient-to-br from-indigo-900 via-purple-900 to-black min-h-screen flex items-center justify-center p-6">
+
+    <div class="max-w-md w-full bg-white/10 backdrop-blur-lg rounded-3xl p-8 shadow-2xl border border-white/20">
+        <h1 class="text-3xl font-bold text-white mb-2 text-center">Audio to Text</h1>
+        <p class="text-purple-200 text-center mb-8 text-sm">Upload your MP3 or WAV and let AI do the rest.</p>
+
+        <form method="POST" enctype="multipart/form-data" class="space-y-6">
+            {% csrf_token %}
+            
+            <!-- Upload Area -->
+            <div class="relative group">
+                <label id="drop-zone" class="flex flex-col items-center justify-center w-full h-48 border-2 border-dashed border-purple-400/50 rounded-2xl cursor-pointer hover:bg-white/5 hover:border-purple-300 transition-all">
+                    <div class="flex flex-col items-center justify-center pt-5 pb-6">
+                        <svg id="upload-icon" class="w-12 h-12 mb-3 text-purple-300" fill="none" stroke="currentColor" viewBox="0 0 24 24">
+                            <path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M7 16a4 4 0 01-.88-7.903A5 5 0 1115.9 6L16 6a5 5 0 011 9.9M15 13l-3-3m0 0l-3 3m3-3v12"></path>
+                        </svg>
+                        <p id="file-name" class="text-sm text-gray-300 px-4 text-center">Click to upload or drag and drop</p>
+                    </div>
+                    <input type="file" id="audio-input" name="audio" class="hidden" accept="audio/*" required />
+                </label>
+            </div>
+
+            <!-- Audio Preview Player (Hidden by default) -->
+            <div id="preview-container" class="hidden animate-fade-in">
+                <p class="text-xs text-purple-300 mb-2 font-semibold uppercase tracking-wider">File Preview:</p>
+                <audio id="audio-preview" controls class="w-full h-10 rounded-lg bg-white/5"></audio>
+            </div>
+
+            <button type="submit" class="w-full py-4 bg-gradient-to-r from-purple-500 to-indigo-600 text-white font-bold rounded-xl shadow-lg hover:from-purple-600 hover:to-indigo-700 transform hover:-translate-y-1 transition-all">
+                Start Transcription
+            </button>
+        </form>
+    </div>
+
+    <script>
+        // Add this to your existing script
+        const form = document.querySelector('form');
+        const button = document.querySelector('button[type="submit"]');
+
+        form.addEventListener('submit', function() {
+            button.disabled = true;
+            button.innerHTML = `
+                <svg class="animate-spin h-5 w-5 mr-3 inline-block border-2 border-t-transparent border-white rounded-full" viewBox="0 0 24 24"></svg>
+                Processing Audio...
+            `;
+            button.classList.add('opacity-75', 'cursor-not-allowed');
+        });
+        const audioInput = document.getElementById('audio-input');
+        const fileName = document.getElementById('file-name');
+        const previewContainer = document.getElementById('preview-container');
+        const audioPreview = document.getElementById('audio-preview');
+        const dropZone = document.getElementById('drop-zone');
+
+        audioInput.addEventListener('change', function() {
+            const file = this.files[0];
+            if (file) {
+                // Update text to show file name
+                fileName.textContent = `Selected: ${file.name}`;
+                fileName.classList.remove('text-gray-300');
+                fileName.classList.add('text-green-400', 'font-medium');
+
+                // Show and load the audio preview
+                const url = URL.createObjectURL(file);
+                audioPreview.src = url;
+                previewContainer.classList.remove('hidden');
+                
+                // Change border color to show success
+                dropZone.classList.remove('border-purple-400/50');
+                dropZone.classList.add('border-green-500/50');
+            }
+        });
+    </script>
+
+    <style>
+        .animate-fade-in {
+            animation: fadeIn 0.5s ease-in-out;
+        }
+        @keyframes fadeIn {
+            from { opacity: 0; transform: translateY(10px); }
+            to { opacity: 1; transform: translateY(0); }
+        }
+        /* Custom styling for the audio player to match the theme */
+        audio::-webkit-media-controls-panel {
+            background-color: rgba(255, 255, 255, 0.1);
+        }
+    </style>
+</body>
+</html>

transcriber/tests.py

@@ -0,0 +1,3 @@
+from django.test import TestCase
+
+# Create your tests here.

transcriber/urls.py

@@ -0,0 +1,6 @@
+from django.urls import path
+from . import views
+
+urlpatterns = [
+    path('', views.transcribe_audio, name='upload_audio'),
+]

transcriber/views.py

@@ -0,0 +1,25 @@
+from django.shortcuts import render
+from .models import Transcription
+from faster_whisper import WhisperModel
+import os
+
+# Load model ONCE globally (outside the view) to save time
+# 'int8' quantization makes it much faster on CPU
+model = WhisperModel("base", device="cpu", compute_type="int8")
+
+def transcribe_audio(request):
+    if request.method == 'POST' and request.FILES.get('audio'):
+        audio_obj = Transcription.objects.create(audio_file=request.FILES['audio'])
+        
+        # transcribe returns a generator of segments
+        segments, info = model.transcribe(audio_obj.audio_file.path, beam_size=5)
+        
+        # Combine all segments into one full string
+        full_text = "".join([segment.text for segment in segments])
+        
+        audio_obj.transcript_text = full_text.strip()
+        audio_obj.save()
+        
+        return render(request, 'result.html', {'transcription': audio_obj})
+    
+    return render(request, 'upload.html')