Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -1,52 +1,35 @@
|
|
1 |
-
import
|
2 |
-
import os
|
3 |
-
import queue
|
4 |
-
import sounddevice as sd
|
5 |
import numpy as np
|
6 |
-
import
|
7 |
from sentence_transformers import SentenceTransformer
|
8 |
from sklearn.metrics.pairwise import cosine_similarity
|
9 |
-
import json
|
10 |
import PyPDF2
|
11 |
|
12 |
-
#
|
13 |
-
|
14 |
-
|
15 |
-
HF_API_KEY = os.getenv('HF_API_KEY') # Replace with your Hugging Face API key
|
16 |
-
|
17 |
-
# Parameters
|
18 |
-
silence_threshold = 0.01 # Silence threshold for audio detection
|
19 |
-
silence_duration = 2.0 # Duration of silence to detect end of speech
|
20 |
-
sample_rate = 16000 # Audio sample rate
|
21 |
-
|
22 |
-
# Audio buffer
|
23 |
-
audio_queue = queue.Queue()
|
24 |
|
25 |
# Load a pre-trained model for vector embeddings
|
26 |
embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
|
27 |
|
28 |
# Parse PDF and create resume content
|
29 |
-
def parse_resume(
|
30 |
-
"""Extract text from
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
return {}
|
40 |
-
|
41 |
-
# Load vector database (resume content)
|
42 |
-
def load_resume(pdf_path):
|
43 |
-
resume_content = parse_resume(pdf_path)
|
44 |
resume_embeddings = {
|
45 |
section: embedding_model.encode(content) for section, content in resume_content.items()
|
46 |
}
|
47 |
return resume_embeddings
|
48 |
|
49 |
-
|
|
|
50 |
"""Find the most relevant section in the resume and generate a question."""
|
51 |
user_embedding = embedding_model.encode(user_input)
|
52 |
similarities = {
|
@@ -56,105 +39,20 @@ def get_relevant_question(user_input, resume_embeddings):
|
|
56 |
most_relevant_section = max(similarities, key=similarities.get)
|
57 |
return f"Based on your experience in {most_relevant_section}, can you elaborate more?"
|
58 |
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
try:
|
74 |
-
# Fetch audio data
|
75 |
-
data = audio_queue.get()
|
76 |
-
buffer.append(data)
|
77 |
-
|
78 |
-
# Check for silence
|
79 |
-
rms = np.sqrt(np.mean(data**2))
|
80 |
-
if rms < silence_threshold:
|
81 |
-
if silence_start is None:
|
82 |
-
silence_start = time.time()
|
83 |
-
elif time.time() - silence_start > silence_duration:
|
84 |
-
print("Silence detected. Stopping recording.")
|
85 |
-
break
|
86 |
-
else:
|
87 |
-
silence_start = None
|
88 |
-
|
89 |
-
except KeyboardInterrupt:
|
90 |
-
print("Recording stopped by user.")
|
91 |
-
break
|
92 |
-
|
93 |
-
audio_data = np.concatenate(buffer, axis=0)
|
94 |
-
return audio_data
|
95 |
-
|
96 |
-
def transcribe_audio(audio_data):
|
97 |
-
"""Transcribe audio to text using Hugging Face Whisper API."""
|
98 |
-
print("Transcribing audio...")
|
99 |
-
headers = {"Authorization": f"Bearer {HF_API_KEY}"}
|
100 |
-
response = requests.post(
|
101 |
-
HF_API_URL_STT,
|
102 |
-
headers=headers,
|
103 |
-
data=audio_data.tobytes(),
|
104 |
-
)
|
105 |
-
if response.status_code == 200:
|
106 |
-
return response.json().get("text", "")
|
107 |
-
else:
|
108 |
-
print(f"Error: {response.status_code} {response.text}")
|
109 |
-
return ""
|
110 |
-
|
111 |
-
def generate_question(response, resume_embeddings):
|
112 |
-
"""Generate a question based on the user's response using Hugging Face API."""
|
113 |
-
if resume_embeddings:
|
114 |
-
return get_relevant_question(response, resume_embeddings)
|
115 |
-
|
116 |
-
print("Generating a question...")
|
117 |
-
headers = {"Authorization": f"Bearer {HF_API_KEY}"}
|
118 |
-
payload = {"inputs": {"past_user_inputs": [""], "generated_responses": [""], "text": response}}
|
119 |
-
response = requests.post(
|
120 |
-
HF_API_URL_CONVERSATION,
|
121 |
-
headers=headers,
|
122 |
-
json=payload
|
123 |
-
)
|
124 |
-
if response.status_code == 200:
|
125 |
-
return response.json().get("generated_text", "Could you elaborate on that?")
|
126 |
-
else:
|
127 |
-
print(f"Error: {response.status_code} {response.text}")
|
128 |
-
return "Sorry, I couldn't generate a question."
|
129 |
-
|
130 |
-
def main():
|
131 |
-
print("Mock Interview System Initialized")
|
132 |
-
|
133 |
-
# Load the resume embeddings
|
134 |
-
pdf_path = "resume.pdf" # Replace with the path to your PDF resume file
|
135 |
-
if os.path.exists(pdf_path):
|
136 |
-
print("Loading resume...")
|
137 |
-
resume_embeddings = load_resume(pdf_path)
|
138 |
-
else:
|
139 |
-
print("Resume file not found. Proceeding without it.")
|
140 |
-
resume_embeddings = None
|
141 |
-
|
142 |
-
while True:
|
143 |
-
try:
|
144 |
-
# Record audio
|
145 |
-
audio_data = record_audio()
|
146 |
-
|
147 |
-
# Transcribe to text
|
148 |
-
response = transcribe_audio(audio_data)
|
149 |
-
print(f"You said: {response}")
|
150 |
-
|
151 |
-
# Generate and ask the next question
|
152 |
-
question = generate_question(response, resume_embeddings)
|
153 |
-
print(f"Interview AI: {question}")
|
154 |
-
|
155 |
-
except Exception as e:
|
156 |
-
print(f"Error: {e}")
|
157 |
-
break
|
158 |
|
159 |
if __name__ == "__main__":
|
160 |
-
|
|
|
1 |
+
import gradio as gr
|
|
|
|
|
|
|
2 |
import numpy as np
|
3 |
+
from transformers import pipeline
|
4 |
from sentence_transformers import SentenceTransformer
|
5 |
from sklearn.metrics.pairwise import cosine_similarity
|
|
|
6 |
import PyPDF2
|
7 |
|
8 |
+
# Load local models for inference
|
9 |
+
stt_model = pipeline("automatic-speech-recognition", model="openai/whisper-base")
|
10 |
+
conversation_model = pipeline("conversational", model="facebook/blenderbot-400M-distill")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
# Load a pre-trained model for vector embeddings
|
13 |
embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
|
14 |
|
15 |
# Parse PDF and create resume content
|
16 |
+
def parse_resume(pdf):
|
17 |
+
"""Extract text from an uploaded PDF file."""
|
18 |
+
reader = PyPDF2.PdfReader(pdf)
|
19 |
+
text = "\n".join(page.extract_text() for page in reader.pages if page.extract_text())
|
20 |
+
sections = {"Resume Content": text}
|
21 |
+
return sections
|
22 |
+
|
23 |
+
# Process resume and generate embeddings
|
24 |
+
def process_resume(pdf):
|
25 |
+
resume_content = parse_resume(pdf)
|
|
|
|
|
|
|
|
|
|
|
26 |
resume_embeddings = {
|
27 |
section: embedding_model.encode(content) for section, content in resume_content.items()
|
28 |
}
|
29 |
return resume_embeddings
|
30 |
|
31 |
+
# Generate question from user response
|
32 |
+
def generate_question(user_input, resume_embeddings):
|
33 |
"""Find the most relevant section in the resume and generate a question."""
|
34 |
user_embedding = embedding_model.encode(user_input)
|
35 |
similarities = {
|
|
|
39 |
most_relevant_section = max(similarities, key=similarities.get)
|
40 |
return f"Based on your experience in {most_relevant_section}, can you elaborate more?"
|
41 |
|
42 |
+
# Gradio interface
|
43 |
+
def mock_interview(audio, pdf):
|
44 |
+
resume_embeddings = process_resume(pdf)
|
45 |
+
transcription = stt_model(audio)["text"]
|
46 |
+
question = generate_question(transcription, resume_embeddings)
|
47 |
+
return transcription, question
|
48 |
+
|
49 |
+
interface = gr.Interface(
|
50 |
+
fn=mock_interview,
|
51 |
+
inputs=[gr.Audio(source="microphone", type="filepath"), gr.File(label="Upload Resume (PDF)")],
|
52 |
+
outputs=["text", "text"],
|
53 |
+
title="Mock Interview AI",
|
54 |
+
description="Upload your resume and answer questions in a mock interview."
|
55 |
+
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
if __name__ == "__main__":
|
58 |
+
interface.launch()
|