Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import openai | |
| from langdetect import detect | |
| from transformers import pipeline | |
| import os | |
| openai.api_key = os.getenv("OPENAI_API_KEY") # Set this in HF Space secrets | |
| summarizer = pipeline("summarization", model="facebook/bart-large-cnn") | |
| def make_str(val): | |
| # Always return string, even if val is None, bool, list, dict, etc. | |
| 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): | |
| # Accept only valid, non-empty file path (string) | |
| 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 (make_str(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 = make_str(f"Error translating: {e}") | |
| try: | |
| summary = summarizer(transcript_en, max_length=100, min_length=30, do_sample=False) | |
| # Make sure we always extract a string summary, never bool/None/etc. | |
| if isinstance(summary, list) and len(summary) > 0 and "summary_text" in summary[0]: | |
| summary_text = make_str(summary[0]["summary_text"]) | |
| else: | |
| summary_text = make_str(summary) | |
| except Exception as e: | |
| summary_text = make_str(f"Error summarizing: {e}") | |
| # Return only strings, never bool/None/dict/list | |
| return (make_str(lang_text), make_str(transcript), make_str(transcript_en), make_str(summary_text)) | |
| 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="Summary"), | |
| ], | |
| title="Audio Transcript, Translation & Summary (via OpenAI Whisper API)", | |
| description="Upload your audio file (MP3/WAV). This app transcribes via OpenAI Whisper API, detects language, translates to English if needed, and summarizes." | |
| ) | |
| iface.launch() | |