Upload 14 files

app.py

@@ -0,0 +1,167 @@
+import whisper
+import gradio as gr
+import torch
+from transformers import BertTokenizer, BertForSequenceClassification
+from app.questions import get_question
+
+# Load Whisper model
+whisper_model = whisper.load_model("small")
+
+# Load the pre-trained model and tokenizer for confidence analysis
+confidence_model = BertForSequenceClassification.from_pretrained('RiteshAkhade/confidence_model')
+confidence_tokenizer = BertTokenizer.from_pretrained('RiteshAkhade/confidence_model')
+
+# Load pre-trained context analysis model (BERT-based)
+context_model = BertForSequenceClassification.from_pretrained('RiteshAkhade/context_model')
+context_tokenizer = BertTokenizer.from_pretrained('RiteshAkhade/context_model')
+
+# Function to perform context analysis using the BERT model
+def predict_relevance(question, answer):
+    if not answer.strip():  # Check for empty answers
+        return "Irrelevant"
+    
+    inputs = context_tokenizer(question, answer, return_tensors="pt", padding=True, truncation=True)
+    context_model.eval()
+
+    with torch.no_grad():
+        outputs = context_model(**inputs)
+        logits = outputs.logits
+        probabilities = torch.softmax(logits, dim=-1)
+        threshold = 0.5
+        relevant_prob = probabilities[0, 1]  # Probability for relevant class
+    
+    if relevant_prob > threshold:
+        return "Relevant"
+    else:
+        return "Irrelevant"
+
+# Function to perform confidence analysis
+def predict_confidence(question, answer):
+    inputs = confidence_tokenizer(question, answer, return_tensors="pt", padding=True, truncation=True)
+    confidence_model.eval()
+
+    with torch.no_grad():
+        outputs = confidence_model(**inputs)
+        logits = outputs.logits
+        predictions = torch.argmax(logits, dim=-1)
+        return "Confident" if predictions.item() == 1 else "Not Confident"
+
+# Questions from questions.py
+def fetch_questions():
+    return [get_question(i) for i in range(6)]
+
+questions = fetch_questions()
+current_question_index = 0
+
+# Function to show the current question
+def show_question():
+    global current_question_index
+    question = questions[current_question_index]
+    return question
+
+# Function to move to the next question
+def next_question():
+    global current_question_index
+    current_question_index = (current_question_index + 1) % len(questions)
+    return show_question(), None, "", "", ""
+
+# Function to transcribe the audio input and perform both context and confidence analyses
+def transcribe_and_analyze(audio, question):
+    try:
+        # Load and process audio using Whisper
+        audio = whisper.load_audio(audio)
+        audio = whisper.pad_or_trim(audio)
+        mel = whisper.log_mel_spectrogram(audio).to(whisper_model.device)
+        options = whisper.DecodingOptions(fp16=False)
+        result = whisper.decode(whisper_model, mel, options)
+        
+        # Get the transcribed text
+        transcribed_text = result.text
+
+        # Perform context and confidence analysis
+        context_result = predict_relevance(question, transcribed_text)
+        confidence_result = predict_confidence(question, transcribed_text)
+
+        # Return the results
+        return transcribed_text, context_result, confidence_result
+    except Exception as e:
+        return f"Error: {str(e)}", "", ""
+
+#  Gradio interface 
+with gr.Blocks() as demo:
+    
+    gr.HTML('''
+    <style>
+        body { 
+            background-color: #f0f0f0; 
+        }
+        #title { 
+            color: grey; 
+            font-size: 30px; 
+            text-align: center; 
+            margin-bottom: 20px; 
+        }
+        .transcribe-btn, .next-btn { 
+            background-color: #4CAF50; 
+            color: white; 
+            font-size: 16px; 
+            padding: 10px 20px; 
+            border-radius: 5px; 
+            cursor: pointer; 
+            margin-top: 10px;
+        }
+        .transcribe-btn:hover, .next-btn:hover { 
+            background-color: #45a049; 
+        }
+        #question-box { 
+            font-size: 20px; 
+            color: #555; 
+            text-align: center; 
+        }
+        #text-box {
+            font-size: 18px;
+            color: #333;
+        }
+        #context-box, #confidence-box {
+            font-size: 18px;
+            color: #333;
+        }
+    </style>
+    ''')
+
+    # Title
+    gr.Markdown("<h1 id='title'>INTERVIEW PREPARATION MODEL</h1>")
+
+    # Question display
+    with gr.Row():
+        question_display = gr.Textbox(label="Interview Question", value=show_question(), interactive=False, elem_id="question-box")
+
+    # Audio input and transcription section
+    with gr.Row():
+        audio_input = gr.Audio(type="filepath", label="Record Your Answer")
+
+    # Separate text boxes for the transcribed text, context, and confidence analysis
+    with gr.Row():
+        transcribed_text = gr.Textbox(label="Your Answer (Transcription)", interactive=False, lines=5, elem_id="text-box")
+    
+    with gr.Row():
+        context_analysis_result = gr.Textbox(label="Context Analysis", interactive=False, elem_id="context-box")
+    
+    with gr.Row():
+        confidence_analysis_result = gr.Textbox(label="Confidence Analysis", interactive=False, elem_id="confidence-box")
+    
+    # Automatically transcribe the audio and analyze context and confidence when audio is provided
+    audio_input.change(fn=transcribe_and_analyze, 
+                       inputs=[audio_input, question_display], 
+                       outputs=[transcribed_text, context_analysis_result, confidence_analysis_result])
+
+    # Button to get the next question
+    with gr.Row():    
+        next_button = gr.Button("Next Question", elem_classes="next-btn")
+        
+        # Clear audio, transcription, context, and confidence when moving to the next question
+        next_button.click(next_question, 
+                          outputs=[question_display, audio_input, transcribed_text, context_analysis_result, confidence_analysis_result])
+
+# Launch app
+demo.launch(share=True)

app/confidence_analysis.py

@@ -0,0 +1,22 @@
+from transformers import BertTokenizer, BertForSequenceClassification
+import torch
+
+
+
+model = BertForSequenceClassification.from_pretrained('./confidence_model')
+tokenizer = BertTokenizer.from_pretrained('./confidence_tokenizer')
+
+def predict_confidence(question, answer):
+    inputs = tokenizer(question, answer, return_tensors="pt", padding=True, truncation=True)
+    model.eval()
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+        predictions = torch.argmax(logits, dim=-1)
+        return "Confident" if predictions.item() == 1 else "Not Confident"
+
+# Example
+question = "What is your experience with Python?"
+answer = "I dont have any experience in Python"
+print(predict_confidence(question, answer))

app/context_analysis.py

@@ -0,0 +1,40 @@
+from transformers import BertTokenizer, BertForSequenceClassification
+import torch
+
+
+
+
+model = BertForSequenceClassification.from_pretrained('./test_model')
+
+tokenizer = BertForSequenceClassification.from_pretrained('./test_tokenizer')
+
+
+def predict_relevance(question, answer):
+
+    if not answer.strip():  # Check for empty answers
+        return "Irrelevant"
+    
+
+    inputs = tokenizer(question, answer, return_tensors="pt", padding=True, truncation=True)
+    model.eval()
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+        probabilities = torch.softmax(logits, dim=-1)
+        # Adjust the threshold 
+        threshold = 0.5
+        prediction = torch.argmax(probabilities, dim=-1)
+        relevant_prob = probabilities[0, 1]  # Probability for relevant class
+    
+    #threshold logic
+    if relevant_prob > threshold:
+        return "Relevant"
+    else:
+        return "Irrelevant"
+
+# Example 
+question = "What is your experience with Python?"
+answer = "I have minimal experience with java, mostly for small automation tasks."  # Empty answer
+result = predict_relevance(question, answer)
+print(f"Relevance: {result}")

app/questions.py

@@ -0,0 +1,22 @@
+# app/questions.py
+
+# List of interview questions
+questions = [
+    "What is your experience with Python?",
+    "Can you explain the concept of OOP?",
+    "Describe a time you faced a challenge and how you overcame it.",
+    "What are your strengths and weaknesses?",
+    "How do you handle working under pressure?",
+    "What are your career goals in the next five years?"
+]
+
+# Function to get a question based on an index or randomly
+def get_question(index=None):
+    if index is not None and 0 <= index < len(questions):
+        return questions[index]
+    else:
+        return "Invalid question index."
+
+# Option to get the next question from the list
+def get_all_questions():
+    return questions

requirement.txt

@@ -0,0 +1,140 @@
+accelerate==1.0.1
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.3
+aiohttp==3.10.10
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==4.6.0
+asttokens==2.4.1
+attrs==24.2.0
+blinker==1.8.2
+captcha==0.6.0
+certifi==2024.8.30
+cffi==1.17.1
+charset-normalizer==3.3.2
+click==8.1.7
+cmudict==1.0.31
+comm==0.2.2
+datasets==3.0.1
+debugpy==1.8.7
+decorator==5.1.1
+dill==0.3.8
+executing==2.1.0
+fastapi==0.115.0
+ffmpy==0.4.0
+filelock==3.16.1
+Flask==3.0.3
+frozenlist==1.4.1
+fsspec==2024.6.1
+gradio==5.0.2
+gradio_client==1.4.0
+gTTS==2.5.3
+h11==0.14.0
+httpcore==1.0.6
+httpx==0.27.2
+huggingface-hub==0.25.1
+idna==3.10
+importlib_metadata==8.5.0
+importlib_resources==6.4.5
+ipykernel==6.29.5
+ipython==8.29.0
+itsdangerous==2.2.0
+jedi==0.19.1
+Jinja2==3.1.4
+joblib==1.4.2
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+language_tool_python==2.8.1
+llvmlite==0.43.0
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+more-itertools==10.5.0
+mpmath==1.3.0
+multidict==6.1.0
+multiprocess==0.70.16
+nest-asyncio==1.6.0
+networkx==3.3
+nltk==3.9.1
+numba==0.60.0
+numpy==2.0.2
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.77
+nvidia-nvtx-cu12==12.1.105
+openai-whisper @ git+https://github.com/openai/whisper.git@25639fc17ddc013d56c594bfbf7644f2185fad84
+orjson==3.10.7
+packaging==24.1
+pandas==2.2.3
+parso==0.8.4
+pexpect==4.9.0
+pillow==10.4.0
+platformdirs==4.3.6
+prompt_toolkit==3.0.48
+pronouncing==0.2.0
+propcache==0.2.0
+psutil==6.1.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyarrow==17.0.0
+PyAudio==0.2.14
+pycparser==2.22
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+python-dateutil==2.9.0.post0
+python-multipart==0.0.12
+pytz==2024.2
+PyYAML==6.0.2
+pyzmq==26.2.0
+regex==2024.9.11
+requests==2.32.3
+rich==13.9.2
+ruff==0.6.9
+safetensors==0.4.5
+scikit-learn==1.5.2
+scipy==1.14.1
+semantic-version==2.10.0
+setuptools==75.1.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+sounddevice==0.5.0
+SpeechRecognition==3.10.4
+stack-data==0.6.3
+starlette==0.38.6
+sympy==1.13.3
+textblob==0.18.0.post0
+threadpoolctl==3.5.0
+tiktoken==0.8.0
+tokenizers==0.20.0
+tomlkit==0.12.0
+torch==2.4.1
+tornado==6.4.1
+tqdm==4.66.5
+traitlets==5.14.3
+transformers==4.45.1
+triton==3.0.0
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.31.1
+vaderSentiment==3.3.2
+wcwidth==0.2.13
+websockets==12.0
+Werkzeug==3.0.4
+wheel==0.44.0
+xxhash==3.5.0
+yarl==1.15.4
+zipp==3.20.2