Spaces:
Sleeping
Sleeping
File size: 4,333 Bytes
bcd1dcf 1507087 bcd1dcf 1507087 bcd1dcf 1507087 6b80a5d bcd1dcf 042bc75 bcd1dcf 19e07c9 bcd1dcf 19e07c9 bcd1dcf 612bb17 bcd1dcf |
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 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 |
import gradio as gr
import requests
from fpdf import FPDF
import nltk
import os
import tempfile
from nltk.tokenize import sent_tokenize
import random
# Attempt to download punkt tokenizer
try:
nltk.download("punkt")
except:
print("NLTK punkt tokenizer download failed. Using custom tokenizer.")
def custom_sent_tokenize(text):
return text.split(". ")
def transcribe(audio_path):
with open(audio_path, "rb") as audio_file:
audio_data = audio_file.read()
groq_api_endpoint = "https://api.groq.com/openai/v1/audio/transcriptions"
headers = {
"Authorization": "Bearer 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", # Replace with your actual API key
}
files = {
'file': ('audio.wav', audio_data, 'audio/wav'),
}
data = {
'model': 'whisper-large-v3-turbo',
'response_format': 'json',
'language': 'en',
}
response = requests.post(groq_api_endpoint, headers=headers, files=files, data=data)
if response.status_code == 200:
result = response.json()
transcript = result.get("text", "No transcription available.")
return generate_notes(transcript)
else:
error_msg = response.json().get("error", {}).get("message", "Unknown error.")
print(f"API Error: {error_msg}")
return create_error_pdf(f"API Error: {error_msg}")
def generate_notes(transcript):
try:
sentences = sent_tokenize(transcript)
except LookupError:
sentences = custom_sent_tokenize(transcript)
long_questions = [f"What is meant by '{sentence}'?" for sentence in sentences[:5]]
short_questions = [f"Define '{sentence.split()[0]}'." for sentence in sentences[:5]]
mcqs = []
for sentence in sentences[:5]:
mcq = {
"question": f"What is '{sentence.split()[0]}'?",
"options": [sentence.split()[0]] + random.sample(["Option 1", "Option 2", "Option 3"], 3),
"answer": sentence.split()[0]
}
mcqs.append(mcq)
pdf_path = create_pdf(transcript, long_questions, short_questions, mcqs)
return pdf_path
def create_pdf(transcript, long_questions, short_questions, mcqs):
pdf = FPDF()
pdf.add_page()
pdf.set_font("Arial", "B", 16)
pdf.cell(200, 10, "Transcription Notes", ln=True, align="C")
pdf.set_font("Arial", "", 12)
pdf.multi_cell(0, 10, f"Transcription:\n{transcript.encode('latin1', 'replace').decode('latin1')}\n\n")
pdf.set_font("Arial", "B", 14)
pdf.cell(200, 10, "Long Questions", ln=True)
pdf.set_font("Arial", "", 12)
for question in long_questions:
pdf.multi_cell(0, 10, f"- {question.encode('latin1', 'replace').decode('latin1')}\n")
pdf.set_font("Arial", "B", 14)
pdf.cell(200, 10, "Short Questions", ln=True)
pdf.set_font("Arial", "", 12)
for question in short_questions:
pdf.multi_cell(0, 10, f"- {question.encode('latin1', 'replace').decode('latin1')}\n")
pdf.set_font("Arial", "B", 14)
pdf.cell(200, 10, "Multiple Choice Questions (MCQs)", ln=True)
pdf.set_font("Arial", "", 12)
for mcq in mcqs:
pdf.multi_cell(0, 10, f"Q: {mcq['question'].encode('latin1', 'replace').decode('latin1')}")
for option in mcq["options"]:
pdf.multi_cell(0, 10, f" - {option.encode('latin1', 'replace').decode('latin1')}")
pdf.multi_cell(0, 10, f"Answer: {mcq['answer'].encode('latin1', 'replace').decode('latin1')}\n")
with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_pdf:
pdf.output(temp_pdf.name)
pdf_path = temp_pdf.name
return pdf_path
def create_error_pdf(message):
pdf = FPDF()
pdf.add_page()
pdf.set_font("Arial", "B", 16)
pdf.cell(200, 10, "Error Report", ln=True, align="C")
pdf.set_font("Arial", "", 12)
pdf.multi_cell(0, 10, message.encode('latin1', 'replace').decode('latin1'))
with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as temp_pdf:
pdf.output(temp_pdf.name)
error_pdf_path = temp_pdf.name
return error_pdf_path
iface = gr.Interface(
fn=transcribe,
inputs=gr.Audio(type="filepath"),
outputs=gr.File(label="Download PDF with Notes or Error Report"),
title="Voice to Text Converter and Notes Generator",
)
iface.launch() |