Update app.py

app.py

@@ -1,64 +1,91 @@
+# Import required libraries
+from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
 import gradio as gr
-from huggingface_hub import InferenceClient
+import matplotlib.pyplot as plt
+import pandas as pd
+from speechbrain.pretrained import Tacotron2, HIFIGAN, EncoderDecoderASR
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient(model="meta-llama/Llama-3.2-3B")
+# Load Hugging Face psychometric model
+psych_model_name = "KevSun/Personality_LM"  # Big Five personality traits
+psych_model = pipeline("text-classification", model=psych_model_name)
 
+# Load ASR model
+asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-crdnn-rnnlm-librispeech", savedir="tmp_asr")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Load TTS model
+tts_model = Tacotron2.from_hparams(source="speechbrain/tts-tacotron2-ljspeech", savedir="tmp_tts")
+voc_model = HIFIGAN.from_hparams(source="speechbrain/tts-hifigan-ljspeech", savedir="tmp_voc")
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# Psychometric Test Questions
+text_questions = [
+    "How do you handle criticism?",
+    "Describe a time when you overcame a challenge.",
+    "What motivates you to work hard?"
+]
 
-    messages.append({"role": "user", "content": message})
+audio_questions = [
+    "What does teamwork mean to you?",
+    "How do you handle stressful situations?"
+]
 
-    response = ""
+# Function to analyze text response
+def analyze_text_responses(responses):
+    analysis = [psych_model(response)[0] for response in responses]
+    traits = {response["label"]: response["score"] for response in analysis}
+    return traits
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+# Function to handle TTS
+def generate_audio_question(question):
+    mel_output, alignment, _ = tts_model.encode_text(question)
+    waveforms = voc_model.decode_batch(mel_output)
+    return waveforms[0].numpy()
 
-        response += token
-        yield response
+# Function to process audio response
+def process_audio_response(audio):
+    text_response = asr_model.transcribe_file(audio)
+    return text_response
 
+# Gradio interface functions
+def text_part(candidate_name, responses):
+    traits = analyze_text_responses(responses)
+    df = pd.DataFrame(traits.items(), columns=["Trait", "Score"])
+    plt.figure(figsize=(8, 6))
+    plt.bar(df["Trait"], df["Score"], color="skyblue")
+    plt.title(f"Psychometric Analysis for {candidate_name}")
+    plt.xlabel("Traits")
+    plt.ylabel("Score")
+    plt.xticks(rotation=45)
+    plt.tight_layout()
+    return df, plt
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+def audio_part(candidate_name, audio_responses):
+    text_responses = [process_audio_response(audio) for audio in audio_responses]
+    traits = analyze_text_responses(text_responses)
+    df = pd.DataFrame(traits.items(), columns=["Trait", "Score"])
+    plt.figure(figsize=(8, 6))
+    plt.bar(df["Trait"], df["Score"], color="lightcoral")
+    plt.title(f"Audio Psychometric Analysis for {candidate_name}")
+    plt.xlabel("Traits")
+    plt.ylabel("Score")
+    plt.xticks(rotation=45)
+    plt.tight_layout()
+    return df, plt
+
+# Gradio UI
+def chat_interface(candidate_name, text_responses, audio_responses):
+    text_df, text_plot = text_part(candidate_name, text_responses)
+    audio_df, audio_plot = audio_part(candidate_name, audio_responses)
+    return text_df, text_plot, audio_df, audio_plot
 
+text_inputs = [gr.Textbox(label=f"Response to Q{i+1}: {q}") for i, q in enumerate(text_questions)]
+audio_inputs = [gr.Audio(label=f"Response to Q{i+1}: {q}", type="file") for i, q in enumerate(audio_questions)]
+
+interface = gr.Interface(
+    fn=chat_interface,
+    inputs=[gr.Textbox(label="Candidate Name")] + text_inputs + audio_inputs,
+    outputs=["dataframe", "plot", "dataframe", "plot"],
+    title="Psychometric Analysis Chatbot"
+)
 
-if __name__ == "__main__":
-    demo.launch()
+# Launch chatbot
+interface.launch()