Update app.py

app.py

@@ -1,150 +1,17 @@
-import os
-import gradio as gr
-import tempfile
-import yt_dlp
-import subprocess
-from pydub import AudioSegment
-from groq import Groq
-
-# ✅ Environment Variables
-GROQ_API_KEY = os.getenv("GROQ_API_KEY")
-if not GROQ_API_KEY:
-    raise EnvironmentError("Please set GROQ_API_KEY.")
-
-groq_client = Groq(api_key=GROQ_API_KEY)
-
-# ✅ Download YouTube Audio
-def download_youtube_audio(youtube_url):
-    with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as tmp_file:
-        ydl_opts = {
-            "format": "bestaudio/best",
-            "outtmpl": tmp_file.name,
-            "quiet": True,
-            "postprocessors": [{
-                "key": "FFmpegExtractAudio",
-                "preferredcodec": "mp3",
-                "preferredquality": "192",
-            }],
-        }
-        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
-            ydl.download([youtube_url])
-        return tmp_file.name
-
-# ✅ Convert to WAV safely
-def convert_to_wav(input_path):
-    try:
-        tmp_wav = tempfile.NamedTemporaryFile(suffix=".wav", delete=False, prefix="conv_")
-        out_wav = tmp_wav.name
-        result = subprocess.run(
-            ["ffmpeg", "-y", "-i", str(input_path), "-ar", "16000", "-ac", "1", out_wav],
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE
-        )
-        if result.returncode != 0:
-            audio = AudioSegment.from_file(input_path)
-            audio = audio.set_frame_rate(16000).set_channels(1)
-            audio.export(out_wav, format="wav")
-        return out_wav
-    except Exception as e:
-        raise RuntimeError(f"❌ Error converting to WAV: {e}")
-
-# ✅ Split long audio into 5-min chunks
-def split_audio(file_path, max_duration_ms=5*60*1000):
-    audio = AudioSegment.from_file(file_path)
-    chunks = []
-    for i in range(0, len(audio), max_duration_ms):
-        chunk = audio[i:i + max_duration_ms]
-        temp_chunk = tempfile.NamedTemporaryFile(suffix=".wav", delete=False)
-        chunk.export(temp_chunk.name, format="wav")
-        chunks.append(temp_chunk.name)
-    return chunks
-
-# ✅ Transcription using Groq Whisper
-def transcribe_audio(audio_path):
-    try:
-        chunks = split_audio(audio_path)
-        transcript = ""
-        for chunk in chunks:
-            with open(chunk, "rb") as f:
-                response = groq_client.audio.transcriptions.create(
-                    model="whisper-large-v3",
-                    file=f
-                )
-            transcript += response.text + "\n"
-        return transcript.strip()
-    except Exception as e:
-        return f"❌ Error during transcription: {e}"
-
-# ✅ Chunk-wise summarization using Groq LLM
-def summarize_text(text, lang):
-    try:
-        chunks = [text[i:i+2000] for i in range(0, len(text), 2000)]
-        summaries = []
-
-        for idx, chunk in enumerate(chunks):
-            prompt = (
-                f"Summarize the following text in English:\n\n{chunk}"
-                if lang == "English"
-                else f"مندرجہ ذیل عبارت کا جامع اور رواں اردو خلاصہ تحریر کریں:\n\n{chunk}"
-            )
-            response = groq_client.chat.completions.create(
-                model="openai/gpt-oss-120b",
-                messages=[{"role": "user", "content": prompt}],
-                temperature=0.6,
-            )
-            summaries.append(response.choices[0].message.content.strip())
-
-        # Meta-summary
-        combined = "\n".join(summaries)
-        final_prompt = (
-            f"Combine and condense these summaries into one clear, fluent English summary:\n\n{combined}"
-            if lang == "English"
-            else f"مندرجہ ذیل خلاصوں کو یکجا کر کے ایک مختصر مگر جامع اردو خلاصہ تحریر کریں:\n\n{combined}"
-        )
-        final_response = groq_client.chat.completions.create(
-            model="openai/gpt-oss-120b",
-            messages=[{"role": "user", "content": final_prompt}],
-            temperature=0.6,
-        )
-        return final_response.choices[0].message.content.strip()
-    except Exception as e:
-        return f"❌ Summarization failed: {e}"
-
-# ✅ Main Function
-def process_input(youtube_url, audio_file, lang):
-    try:
-        if youtube_url:
-            audio_path = download_youtube_audio(youtube_url)
-        elif audio_file:
-            audio_path = audio_file
-        else:
-            return "❌ Please upload an audio or paste YouTube link.", "", ""
-
-        wav_path = convert_to_wav(audio_path)
-        transcript = transcribe_audio(wav_path)
-        if transcript.startswith("❌"):
-            return transcript, "", ""
-
-        summary = summarize_text(transcript, lang)
-        return "✅ Transcription Completed!", transcript, summary
-    except Exception as e:
-        return f"❌ Error: {e}", "", ""
-
-# ✅ Gradio Interface
-with gr.Blocks(title="🎧 Urdu & English Audio Summarizer") as app:
-    gr.Markdown("## 🎧 Transcribe & Summarize English or Urdu Audio / YouTube Videos")
-
-    with gr.Row():
-        youtube_link = gr.Textbox(label="📺 YouTube Link (optional)")
-        lang_choice = gr.Dropdown(["English", "Urdu"], value="English", label="🌐 Summary Language")
-
-    audio_input = gr.Audio(type="filepath", label="🎙️ Upload Audio (optional)")
-    btn = gr.Button("🚀 Transcribe & Summarize")
-
-    status = gr.Textbox(label="Status")
-    transcript_box = gr.Textbox(label="📝 Transcription", lines=8)
-    summary_box = gr.Textbox(label="🧩 Summary", lines=8)
-
-    btn.click(process_input, [youtube_link, audio_input, lang_choice], [status, transcript_box, summary_box])
-
-app.launch()
+---
+title: SmartTranscribe — Rate-limited Urdu/English Summaries
+emoji: 🎙️
+colorFrom: indigo
+colorTo: purple
+sdk: gradio
+sdk_version: "4.44.0"
+app_file: app.py
+pinned: true
+---
+
+# SmartTranscribe
+
+Notes:
+- This version respects Groq tokens-per-minute (TPM) limits by chunking transcripts and rate-limiting requests.
+- You can tweak TPM via env var `GROQ_TPM_LIMIT` (default 8000).
+- You can adjust chunk size via `CHUNK_CHARS` and output size via `OUT_TOKENS_PER_CHUNK`.