app.py

import whisper
import gradio as gr
import openai 
import os
openai.api_key = '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'

# load model and processor

model = whisper.load_model("medium")

def get_completion(prompt, model='gpt-3.5-turbo'):
    messages = [{"role": "user", "content": prompt}]
    response = openai.ChatCompletion.create(
        model = model, 
        messages = messages, 
        temperature = 0, 
        
    ) 
    return response.choices[0].message['content']

def transcribe(audio):
    
    #time.sleep(3)
    # load audio and pad/trim it to fit 30 seconds
    audio = whisper.load_audio(audio)
    audio = whisper.pad_or_trim(audio)

    # make log-Mel spectrogram and move to the same device as the model
    mel = whisper.log_mel_spectrogram(audio).to(model.device)

    # detect the spoken language
    _, probs = model.detect_language(mel)
    print(f"Detected language: {max(probs, key=probs.get)}")

    # decode the audio
    options = whisper.DecodingOptions(fp16 = True)
    result = whisper.decode(model, mel, options)
    return result.text
    
    

# gr.Interface(
#     title = 'Talk to NP', 
#     fn=transcribe, 
#     inputs=[
#         gr.inputs.Audio(source="microphone", type="filepath")
#     ],
#     outputs=[
#         "textbox"
#     ],
#     live=True).launch()


def speech_to_text(speech):
    text = asr(speech)["text"]
    return text


def text_to_sentiment(text):
    return classifier(text)[0]["label"]


demo = gr.Blocks()

with demo:
    audio_file = gr.Audio(type="filepath")
    text1 = gr.Textbox()
    text2 = gr.Textbox()

    prompt = f"""
    You are a world class nurse practitioner. You are provided with text delimited by triple quotes. \
    Summarize the text and put it in a table format with rows as follows: \ 
        
    1. Patient identification: 
    2. Chief complaint: 
    3. Medical history: 
    4. Family history: 
    5. Social history: 
    6. Review of systems: 
    7. Current medications: 
    8. Vaccination status: 
    9. Emotional well-being: 
    10. Patient concerns and expectations: 
    
    \"\"\"{text1}\"\"\"
    """

    b1 = gr.Button("Transcribe audio")
    b2 = gr.Button("Summarize")

    b1.click(transcribe, inputs=audio_file, outputs=text1)
    b2.click(get_completion, inputs=text1, outputs=text2)


demo.launch()