Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import os | |
| from transformers import pipeline | |
| from langdetect import detect | |
| def process_audio(audio_file): | |
| try: | |
| # audio_file is a tuple (file_obj, file_path) | |
| audio_path = audio_file if isinstance(audio_file, str) else audio_file.name | |
| # Transcribe | |
| asr = pipeline("automatic-speech-recognition", model="openai/whisper-large") | |
| result = asr(audio_path) | |
| transcript = result["text"] | |
| except Exception as e: | |
| return "Error in transcription: " + str(e), "", "", "" | |
| try: | |
| detected_lang = detect(transcript) | |
| except Exception: | |
| detected_lang = "unknown" | |
| lang_map = {'en': 'English', 'hi': 'Hindi', 'ta': 'Tamil'} | |
| lang_text = lang_map.get(detected_lang, detected_lang) | |
| transcript_en = transcript | |
| if detected_lang != "en": | |
| try: | |
| asr_translate = pipeline( | |
| "automatic-speech-recognition", | |
| model="openai/whisper-large", | |
| task="translate" | |
| ) | |
| result_translate = asr_translate(audio_path) | |
| transcript_en = result_translate["text"] | |
| except Exception as e: | |
| transcript_en = f"Error translating: {e}" | |
| try: | |
| summarizer = pipeline("summarization", model="facebook/bart-large-cnn") | |
| summary = summarizer(transcript_en, max_length=100, min_length=30, do_sample=False) | |
| summary_text = summary[0]["summary_text"] | |
| except Exception as e: | |
| summary_text = f"Error summarizing: {e}" | |
| # Optionally, remove uploaded file if it's saved on disk | |
| return lang_text, transcript, transcript_en, summary_text | |
| with gr.Blocks() as demo: | |
| gr.Markdown("## Audio Transcript, Translation & Summary (Powered by Whisper + Hugging Face)") | |
| audio_input = gr.Audio(source="upload", type="filepath", label="Upload MP3/WAV Audio") | |
| btn = gr | |