Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from transformers import pipeline | |
| from speechbrain.pretrained import Tacotron2, HIFIGAN, EncoderDecoderASR | |
| import matplotlib.pyplot as plt | |
| import pandas as pd | |
| # Initialize psychometric model | |
| psych_model_name = "KevSun/Personality_LM" | |
| psych_model = pipeline("text-classification", model=psych_model_name) | |
| # Initialize ASR and TTS models | |
| asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-crdnn-rnnlm-librispeech", savedir="tmp_asr") | |
| 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") | |
| # Psychometric Test Questions | |
| text_questions = [ | |
| "How do you handle criticism?", | |
| "Describe a time when you overcame a challenge.", | |
| "What motivates you to work hard?" | |
| ] | |
| audio_questions = [ | |
| "What does teamwork mean to you?", | |
| "How do you handle stressful situations?" | |
| ] | |
| # Function to analyze text responses | |
| 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 | |
| # 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() | |
| # 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 | |
| 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 function | |
| def chat_interface(candidate_name, *responses): | |
| # Separate text responses and audio responses | |
| num_text_questions = len(text_questions) | |
| text_responses = responses[:num_text_questions] | |
| audio_responses = responses[num_text_questions:] | |
| # Process text responses | |
| text_df, text_plot = text_part(candidate_name, text_responses) | |
| # Process audio responses | |
| audio_df, audio_plot = audio_part(candidate_name, audio_responses) | |
| return text_df, text_plot, audio_df, audio_plot | |
| # Create text inputs and audio inputs | |
| 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="filepath") 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" | |
| ) | |
| # Launch the interface | |
| interface.launch() | |