Update app.py

app.py

@@ -6,19 +6,20 @@ import subprocess
 import requests
 from huggingface_hub import InferenceClient
 
-# ----------------------------
-# Initialize Hugging Face clients
-# ----------------------------
+# ---------------------------
+# Model setup
+# ---------------------------
 WHISPER_MODEL = "openai/whisper-large-v3"
 EN_SUMMARY_MODEL = "facebook/bart-large-cnn"
 UR_SUMMARY_MODEL = "openai/gpt-oss-120b"
 
 client = InferenceClient()
 
-# ----------------------------
-# Helpers
-# ----------------------------
+# ---------------------------
+# Helper Functions
+# ---------------------------
 def download_youtube_audio(url: str):
+    """Download YouTube audio as mp3"""
     try:
         tmp = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
         ydl_opts = {
@@ -34,60 +35,63 @@ def download_youtube_audio(url: str):
         raise RuntimeError(f"❌ Error downloading YouTube audio: {e}")
 
 def convert_to_wav(audio_path: str):
+    """Convert any audio to 16kHz mono WAV"""
     wav_path = tempfile.mktemp(suffix=".wav")
     try:
         subprocess.run(
             ["ffmpeg", "-y", "-i", audio_path, "-ar", "16000", "-ac", "1", wav_path],
             check=True,
-            capture_output=True
+            capture_output=True,
         )
         return wav_path
     except subprocess.CalledProcessError as e:
         raise RuntimeError(f"❌ ffmpeg conversion failed: {e}")
 
-# ----------------------------
+# ---------------------------
 # Transcription
-# ----------------------------
+# ---------------------------
 def transcribe_audio(audio_file=None, youtube_url=None):
     try:
         if youtube_url and youtube_url.strip():
             audio_path = download_youtube_audio(youtube_url)
-        else:
+        elif audio_file:
             audio_path = audio_file
-        if not audio_path:
-            return "❌ Please upload or record audio or provide a YouTube link."
+        else:
+            return "❌ Please record, upload, or provide a YouTube link."
 
         wav_path = convert_to_wav(audio_path)
 
-        # --- Try API helper first ---
-        try:
-            result = client.audio_to_text(model=WHISPER_MODEL, audio=wav_path)
-            return result["text"] if isinstance(result, dict) else str(result)
-        except Exception:
-            # --- fallback to HTTP call ---
-            api_url = f"https://api-inference.huggingface.co/models/{WHISPER_MODEL}"
-            headers = {"Authorization": f"Bearer {os.environ.get('HUGGINGFACE_API_TOKEN','')}"}
-            with open(wav_path, "rb") as f:
-                resp = requests.post(api_url, headers=headers, data=f)
-            if resp.status_code != 200:
-                raise RuntimeError(f"HF API error: {resp.text}")
-            data = resp.json()
-            if isinstance(data, list) and len(data) and "text" in data[0]:
-                return data[0]["text"]
+        headers = {
+            "Authorization": f"Bearer {os.environ.get('HUGGINGFACE_API_TOKEN','')}",
+            "Content-Type": "audio/wav"
+        }
+        api_url = f"https://api-inference.huggingface.co/models/{WHISPER_MODEL}"
+
+        with open(wav_path, "rb") as f:
+            response = requests.post(api_url, headers=headers, data=f.read())
+
+        if response.status_code != 200:
+            raise RuntimeError(f"HF API error: {response.text}")
+
+        data = response.json()
+        if isinstance(data, dict) and "text" in data:
+            return data["text"]
+        elif isinstance(data, list) and "text" in data[0]:
+            return data[0]["text"]
+        else:
             return str(data)
     except Exception as e:
         return f"❌ Error during transcription: {e}"
 
-# ----------------------------
+# ---------------------------
 # Summarization
-# ----------------------------
+# ---------------------------
 def summarize_text(text, language):
     try:
         if language == "English":
             result = client.summarization(model=EN_SUMMARY_MODEL, inputs=text, max_new_tokens=1024)
             return result["summary_text"]
         else:
-            # Urdu summary via large model
             resp = client.text_generation(
                 model=UR_SUMMARY_MODEL,
                 prompt=f"مندرجہ ذیل انگریزی متن کا جامع اردو خلاصہ لکھیں:\n\n{text}",
@@ -97,14 +101,15 @@ def summarize_text(text, language):
     except Exception as e:
         return f"❌ Summarization failed: {e}"
 
-# ----------------------------
-# Tutorial Creator
-# ----------------------------
+# ---------------------------
+# Tutorial Generator
+# ---------------------------
 def generate_tutorial(transcription, summary, language):
     try:
         prompt = (
-            f"Write a detailed, beginner-friendly tutorial in {language} based on the following transcription and summary.\n\n"
-            f"Transcription:\n{transcription}\n\nSummary:\n{summary}"
+            f"Create a comprehensive, beginner-friendly tutorial in {language} "
+            f"based on the following transcript and summary.\n\n"
+            f"Transcript:\n{transcription}\n\nSummary:\n{summary}"
         )
         model = UR_SUMMARY_MODEL if language == "Urdu" else EN_SUMMARY_MODEL
         result = client.text_generation(model=model, prompt=prompt, max_new_tokens=2200)
@@ -112,30 +117,31 @@ def generate_tutorial(transcription, summary, language):
     except Exception as e:
         return f"❌ Error generating tutorial: {e}"
 
-# ----------------------------
-# Gradio Interface
-# ----------------------------
+# ---------------------------
+# Gradio UI
+# ---------------------------
 with gr.Blocks(title="🎙️ Smart Transcriber & Tutorial Maker") as demo:
-    gr.Markdown("## 🎧 Smart Transcriber & Tutorial Generator")
+    gr.Markdown("## 🎧 Smart Transcriber, Summarizer & Tutorial Creator")
 
     with gr.Row():
-        audio_in = gr.Audio(sources=["microphone", "upload"], type="filepath", label="🎙️ Record / Upload Audio")
-        yt_link = gr.Textbox(label="🎥 Or paste YouTube link")
+        audio_input = gr.Audio(sources=["microphone", "upload"], type="filepath", label="🎙️ Record or Upload Audio")
+        yt_input = gr.Textbox(label="🎥 Or paste YouTube link")
 
     trans_btn = gr.Button("🚀 Transcribe")
-    transcription = gr.Textbox(label="📝 Transcription", lines=8)
+    transcript_output = gr.Textbox(label="📝 Transcription", lines=8)
 
     with gr.Row():
-        lang = gr.Radio(["English", "Urdu"], value="English", label="Select Summary Language")
+        lang_choice = gr.Radio(["English", "Urdu"], label="Select Summary Language", value="English")
+
     sum_btn = gr.Button("🧠 Generate Detailed Summary")
-    summary_box = gr.Textbox(label="📋 Summary", lines=10)
+    summary_output = gr.Textbox(label="📋 Summary", lines=10)
 
     tut_btn = gr.Button("📘 Create Beginner Tutorial")
-    tutorial_box = gr.Textbox(label="🎓 Tutorial", lines=12)
+    tutorial_output = gr.Textbox(label="🎓 Tutorial", lines=12)
 
-    # Actions
-    trans_btn.click(transcribe_audio, [audio_in, yt_link], transcription)
-    sum_btn.click(summarize_text, [transcription, lang], summary_box)
-    tut_btn.click(generate_tutorial, [transcription, summary_box, lang], tutorial_box)
+    # Button actions
+    trans_btn.click(transcribe_audio, [audio_input, yt_input], transcript_output)
+    sum_btn.click(summarize_text, [transcript_output, lang_choice], summary_output)
+    tut_btn.click(generate_tutorial, [transcript_output, summary_output, lang_choice], tutorial_output)
 
 demo.launch()