Spaces:
Running
Running
| import gradio as gr | |
| import openai | |
| from langdetect import detect | |
| from transformers import pipeline | |
| from keybert import KeyBERT | |
| import os | |
| # --- SETUP --- | |
| openai.api_key = os.getenv("OPENAI_API_KEY") # Set in HF Space Secrets | |
| summarizer = pipeline("summarization", model="facebook/bart-large-cnn") | |
| kw_model = KeyBERT() | |
| # Key Indian brokerages, investment apps, and fintech brands | |
| BRANDS = [ | |
| "Zerodha", "Upstox", "Groww", "Angel One", "Motilal Oswal", "Sharekhan", "5paisa", "ICICI Direct", | |
| "HDFC Securities", "Kotak Securities", "Axis Direct", "IIFL", "Paytm Money", "Edelweiss", "Geojit", | |
| "Fyers", "Alice Blue", "mStock", "Stockal", "Kuvera", "Smallcase", "Jupiter", "Fi", "INDmoney", | |
| "PhonePe", "Paytm", "Google Pay", "BHIM", "MobiKwik", "Cred", "Niyo", "Razorpay", "ETMoney", | |
| "Bajaj Finserv", "SBI Securities", "YES Securities", "IDFC FIRST", "CAMS", "Karvy", "LIC", "ICICI Prudential" | |
| ] | |
| def extract_brands(text): | |
| found = [brand for brand in BRANDS if brand.lower() in text.lower()] | |
| return found if found else ["None detected"] | |
| def extract_topics(text, top_n=5): | |
| keywords = kw_model.extract_keywords(text, top_n=top_n, stop_words='english') | |
| topics = [kw for kw, score in keywords] | |
| return topics if topics else ["None extracted"] | |
| def make_bullets(summary): | |
| sentences = summary.replace("\n", " ").split('. ') | |
| bullets = [f"- {s.strip()}" for s in sentences if s.strip()] | |
| return "\n".join(bullets) | |
| def make_str(val): | |
| try: | |
| if val is None: | |
| return "" | |
| if isinstance(val, (bool, int, float)): | |
| return str(val) | |
| if isinstance(val, list): | |
| return "\n".join([make_str(v) for v in val]) | |
| if isinstance(val, dict): | |
| return str(val) | |
| return str(val) | |
| except Exception: | |
| return "" | |
| def process_audio(audio_path): | |
| if not audio_path or not isinstance(audio_path, str): | |
| return ("No audio file provided.", "", "", "", "", "") | |
| try: | |
| with open(audio_path, "rb") as audio_file: | |
| transcript = openai.audio.transcriptions.create( | |
| model="whisper-1", | |
| file=audio_file, | |
| response_format="text" | |
| ) | |
| transcript = make_str(transcript).strip() | |
| except Exception as e: | |
| return (f"Error in transcription: {e}", "", "", "", "", "") | |
| try: | |
| detected_lang = detect(transcript) | |
| lang_text = {'en': 'English', 'hi': 'Hindi', 'ta': 'Tamil'}.get(detected_lang, detected_lang) | |
| except Exception: | |
| lang_text = "unknown" | |
| transcript_en = transcript | |
| if detected_lang != "en": | |
| try: | |
| with open(audio_path, "rb") as audio_file: | |
| transcript_en = openai.audio.translations.create( | |
| model="whisper-1", | |
| file=audio_file, | |
| response_format="text" | |
| ) | |
| transcript_en = make_str(transcript_en).strip() | |
| except Exception as e: | |
| transcript_en = f"Error translating: {e}" | |
| try: | |
| summary_obj = summarizer(transcript_en, max_length=100, min_length=30, do_sample=False) | |
| summary = summary_obj[0]["summary_text"] if isinstance(summary_obj, list) and "summary_text" in summary_obj[0] else make_str(summary_obj) | |
| except Exception as e: | |
| summary = f"Error summarizing: {e}" | |
| brands = extract_brands(transcript_en) | |
| topics = extract_topics(transcript_en) | |
| key_takeaways = make_bullets(summary) | |
| return ( | |
| lang_text, | |
| transcript, | |
| transcript_en, | |
| ", ".join(brands), | |
| ", ".join(topics), | |
| key_takeaways | |
| ) | |
| iface = gr.Interface( | |
| fn=process_audio, | |
| inputs=gr.Audio(type="filepath", label="Upload MP3/WAV Audio"), | |
| outputs=[ | |
| gr.Textbox(label="Detected Language"), | |
| gr.Textbox(label="Original Transcript"), | |
| gr.Textbox(label="English Transcript (if translated)"), | |
| gr.Textbox(label="Indian Brokerages & Fintech Brands Detected"), | |
| gr.Textbox(label="Key Topics"), | |
| gr.Textbox(label="Bulleted Key Takeaways") | |
| ], | |
| title="Audio to Text & Insights Generation", | |
| description="Upload your audio file (MP3/WAV). Get key insights!" | |
| ) | |
| iface.launch() | |