Spaces:
Running
Running
| import gradio as gr | |
| import requests | |
| from fpdf import FPDF | |
| import nltk | |
| import os | |
| import tempfile | |
| from nltk.tokenize import sent_tokenize | |
| import random | |
| from groq import Groq | |
| api_key = os.environ.get("GROQ_API_KEY") | |
| # 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": f"Bearer {api_key}", # Fix: api_key is used properly | |
| } | |
| 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) | |
| # # Generate long questions | |
| # long_questions = [f"Explain the concept discussed in: '{sentence}'." for sentence in sentences[:5]] | |
| # # Generate short questions | |
| # short_questions = [f"What does '{sentence.split()[0]}' mean in the context of this text?" for sentence in sentences[:5]] | |
| # # Generate MCQs with relevant distractors | |
| # mcqs = [] | |
| # for sentence in sentences[:5]: | |
| # if len(sentence.split()) > 1: # Ensure there are enough words to create meaningful options | |
| # key_word = sentence.split()[0] # Use the first word as a key term | |
| # distractors = ["Term A", "Term B", "Term C"] # Replace with relevant terms if needed | |
| # options = [key_word] + distractors | |
| # random.shuffle(options) # Shuffle options for randomness | |
| # mcq = { | |
| # "question": f"What is '{key_word}' based on the context?", | |
| # "options": options, | |
| # "answer": key_word | |
| # } | |
| # mcqs.append(mcq) | |
| client = Groq(api_key="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") | |
| chat_completion = client.chat.completions.create( | |
| # | |
| # Required parameters | |
| # | |
| messages=[ | |
| # Set an optional system message. This sets the behavior of the | |
| # assistant and can be used to provide specific instructions for | |
| # how it should behave throughout the conversation. | |
| { | |
| "role": "system", | |
| "content": "you are expert question generator from content. Generate one long question,possible number of short questions and mcqs.plz also provide the notes" | |
| }, | |
| # Set a user message for the assistant to respond to. | |
| { | |
| "role": "user", | |
| "content": transcript, | |
| } | |
| ], | |
| # The language model which will generate the completion. | |
| model="llama3-8b-8192", | |
| # | |
| # Optional parameters | |
| # | |
| # Controls randomness: lowering results in less random completions. | |
| # As the temperature approaches zero, the model will become deterministic | |
| # and repetitive. | |
| temperature=0.5, | |
| # The maximum number of tokens to generate. Requests can use up to | |
| # 32,768 tokens shared between prompt and completion. | |
| max_tokens=1024, | |
| # Controls diversity via nucleus sampling: 0.5 means half of all | |
| # likelihood-weighted options are considered. | |
| top_p=1, | |
| # A stop sequence is a predefined or user-specified text string that | |
| # signals an AI to stop generating content, ensuring its responses | |
| # remain focused and concise. Examples include punctuation marks and | |
| # markers like "[end]". | |
| stop=None, | |
| # If set, partial message deltas will be sent. | |
| stream=False, | |
| ) | |
| # Print the completion returned by the LLM. | |
| res=chat_completion.choices[0].message.content | |
| # Generate and save a structured PDF | |
| pdf_path = create_pdf(res,transcript) | |
| return pdf_path | |
| def create_pdf(question,transcript): | |
| pdf = FPDF() | |
| pdf.add_page() | |
| # Add title | |
| pdf.set_font("Arial", "B", 16) | |
| pdf.cell(200, 10, "Transcription Notes and Questions", ln=True, align="C") | |
| # Add transcription content | |
| pdf.set_font("Arial", "", 12) | |
| pdf.multi_cell(0, 10, f"Transcription:\n{transcript.encode('latin1', 'replace').decode('latin1')}\n\n") | |
| # Add long questions | |
| pdf.set_font("Arial", "B", 14) | |
| pdf.cell(200, 10, "Questions", ln=True) | |
| pdf.set_font("Arial", "", 12) | |
| pdf.multi_cell(0, 10, f"- {question.encode('latin1', 'replace').decode('latin1')}\n") | |
| # # Add short questions | |
| # 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") | |
| # # Add MCQs | |
| # 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", | |
| description="This app converts audio to text and generates academic questions including long, short, and multiple-choice questions." | |
| ) | |
| iface.launch() |