Spaces:
Sleeping
Sleeping
File size: 2,489 Bytes
1d6eeba 402772f 1d6eeba 402772f 1d6eeba e227091 310b5ef 2e174b1 8ddae8d 310b5ef 1d6eeba 402772f 1d6eeba 2e174b1 1d6eeba 402772f 1d6eeba e227091 8ddae8d e227091 402772f e227091 2e174b1 e227091 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
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 as a secret in your Space settings
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
def process_audio(audio_path):
if not audio_path or not isinstance(audio_path, str):
return "No audio file provided.", "", "", ""
try:
# Send audio to OpenAI Whisper API
with open(audio_path, "rb") as audio_file:
transcript_response = openai.audio.transcriptions.create(
model="whisper-1",
file=audio_file,
response_format="text"
)
transcript = transcript_response
except Exception as e:
return f"Error in transcription: {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:
# Re-send with task=translate for translation to English
with open(audio_path, "rb") as audio_file:
translation_response = openai.audio.translations.create(
model="whisper-1",
file=audio_file,
response_format="text"
)
transcript_en = translation_response
except Exception as e:
transcript_en = f"Error translating: {e}"
try:
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}"
return lang_text, transcript, transcript_en, 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()
|