File size: 4,914 Bytes
5144ac6 5dc2718 5144ac6 5dc2718 5144ac6 5dc2718 5144ac6 5dc2718 |
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 numpy as np
from transformers import pipeline
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity
import PyPDF2
from TTS.api import TTS # Coqui TTS library
# Initialize TTS model
tts_model = TTS(model_name="tts_models/en/ljspeech/tacotron2-DDC", progress_bar=False, gpu=False)
# Load local models for inference
stt_model = pipeline("automatic-speech-recognition", model="openai/whisper-base")
conversation_model = pipeline("text-generation", model="facebook/blenderbot-400M-distill")
# Load a pre-trained model for vector embeddings
embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
# Parse PDF and create resume content
def parse_resume(pdf):
"""Extract text from an uploaded PDF file."""
reader = PyPDF2.PdfReader(pdf)
text = "\n".join(page.extract_text() for page in reader.pages if page.extract_text())
sections = {"Resume Content": text}
return sections
# Process job description text
def process_job_description(job_desc):
"""Encode the job description for analysis."""
return embedding_model.encode(job_desc)
# Process resume and generate embeddings
def process_resume(pdf):
resume_content = parse_resume(pdf)
resume_embeddings = {
section: embedding_model.encode(content) for section, content in resume_content.items()
}
return resume_embeddings
# Generate question from user response
def generate_question(user_input, resume_embeddings):
"""Find the most relevant section in the resume and generate a question."""
user_embedding = embedding_model.encode(user_input)
similarities = {
section: cosine_similarity([user_embedding], [embedding])[0][0]
for section, embedding in resume_embeddings.items()
}
most_relevant_section = max(similarities, key=similarities.get)
return f"Based on your experience in {most_relevant_section}, can you elaborate more?"
# Generate TTS output
def generate_audio(text):
"""Convert text to audio using Coqui TTS."""
audio_path = "output.wav"
tts_model.tts_to_file(text=text, file_path=audio_path)
return audio_path
# Gradio interface
class MockInterview:
def __init__(self):
self.resume_embeddings = None
self.job_desc_embedding = None
self.interview_active = False
def upload_inputs(self, resume, job_desc):
self.resume_embeddings = process_resume(resume)
self.job_desc_embedding = process_job_description(job_desc)
self.interview_active = True
question = "Tell me about yourself."
audio_output = generate_audio(question)
return "Resume and job description processed. Starting the interview.", audio_output
def conduct_interview(self, audio_file):
if not self.interview_active:
return "Please upload your resume and job description first.", None
# Transcribe audio
transcription = stt_model(audio_file)["text"]
if not transcription.strip():
return "No audio detected. Please try again.", None
# Generate next question
question = generate_question(transcription, self.resume_embeddings)
audio_output = generate_audio(question)
return transcription, audio_output
def end_interview(self):
self.interview_active = False
audio_output = generate_audio("Thank you for participating in the interview. Goodbye!")
return "Interview ended. Thank you for participating.", audio_output
mock_interview = MockInterview()
def upload_inputs(resume, job_desc):
return mock_interview.upload_inputs(resume, job_desc)
def conduct_interview(audio_file):
return mock_interview.conduct_interview(audio_file)
def end_interview():
return mock_interview.end_interview()
interface = gr.Blocks()
with interface:
gr.Markdown("""# Mock Interview AI
Upload your resume and job description, then engage in a realistic audio-based interview simulation.""")
with gr.Row():
resume_input = gr.File(label="Upload Resume (PDF)")
job_desc_input = gr.Textbox(label="Paste Job Description")
upload_button = gr.Button("Upload and Start Interview")
with gr.Row():
audio_input = gr.Audio(type="filepath", label="Respond with Your Answer")
transcription_output = gr.Textbox(label="Transcription")
question_output = gr.Audio(label="Question Audio")
submit_button = gr.Button("Submit Response")
end_button = gr.Button("End Interview")
upload_button.click(upload_inputs, inputs=[resume_input, job_desc_input], outputs=[transcription_output, question_output])
submit_button.click(conduct_interview, inputs=[audio_input], outputs=[transcription_output, question_output])
end_button.click(end_interview, outputs=[transcription_output, question_output])
if __name__ == "__main__":
interface.launch()
|