app.py

import gradio as gr
import whisper
from langchain_openai import ChatOpenAI
from utils import RefineDataSummarizer
import os

def transcript(file_dir, language, model_type):
    model_dir = os.path.join('models', model_type)
    model = whisper.load_model(model_dir)
    result = model.transcribe(file_dir, language=language, task='transcribe')

    lines = [s['text'] for s in result['segments']]
    text = ''
    for line in lines:
        text += f"{line}\n"
    return text


def upload_file(file_paths):
    return file_paths


def summary(text, chunk_num, chunk_overlap, user_api, llm_type):
    if user_api == "Not Provided":
        api_key = os.getenv("openai_api")
    else:
        api_key = user_api
    api_key = api_key.strip()
    llm = ChatOpenAI(temperature=1, openai_api_key=api_key, model_name=llm_type)
    rds = RefineDataSummarizer(llm=llm)
    result = rds.get_summarization(text, chunk_num=chunk_num, chunk_overlap=chunk_overlap)
    return result["output_text"]

with gr.Blocks() as demo:
    with gr.Row(equal_height=False):
        with gr.Column():
            file_output = gr.File()
            upload_button = gr.UploadButton("Click to Upload a File", file_types=["audio", "video"], file_count="single")
            upload_button.upload(upload_file, upload_button, file_output)
            language = gr.Dropdown(
                ["English", "Chinese"], label="Transcript Language", value="English")
            model_type = gr.Dropdown(
                [
                    "tiny.en.pt", 
                    "tiny.pt", 
                    "small.en.pt", 
                    "small.pt",
                    "base.en.pt", 
                    "base.pt",
                    "medium.en.pt", 
                    "medium.pt",
                    "large-v1.pt", 
                    "large-v2.pt",], label="Model Type", value="medium.en.pt")
            TranscriptButton = gr.Button("Transcript", variant="primary")
        
        with gr.Column():
            transcript_text = gr.Textbox(placeholder="Transcript Result", label="Transcript")

            with gr.Accordion(open=False, label=["summary settings"]):
                chunk_num = gr.Number(precision=0, minimum=1, maximum=9999, step=1, label="Chunk Number", value=1)
                chunk_overlap = gr.Number(precision=0, minimum=1, maximum=9999, step=1, label="Chunk Overlap", value=100)       

            with gr.Accordion(open=False, label=["llm settings"]):
                user_api = gr.Textbox(placeholder="If Empty, Use Default Key", label="Your API Key", value="Not Provided")
                llm_type =  gr.Dropdown(
                    [
                    "gpt-3.5-turbo", 
                    "gpt-3.5-turbo-16k", 
                    "gpt-4-1106-preview"
                    ], label="LLM Type", value="gpt-4-1106-preview")
            SunmmaryButton = gr.Button("Summary", variant="primary")
            summary_text = gr.Textbox(placeholder="Summary Result", label="Summary")


    TranscriptButton.click(
        fn=transcript, 
        inputs=[
            file_output,
            language,
            model_type
        ],
        outputs=[transcript_text]
    )
    SunmmaryButton.click(
        fn=summary, 
        inputs=[
            transcript_text,
            chunk_num,
            chunk_overlap,
            user_api,
            llm_type
        ],
        outputs=[summary_text]
    )

demo.launch()