app.py

import os
import tempfile

import torch
import gradio as gr
from transformers import pipeline
from huggingface_hub import InferenceClient


device = 0 if torch.cuda.is_available() else "cpu"

AUDIO_MODEL_NAME = "distil-whisper/distil-large-v3" # faster and very close in performance to the full-size "openai/whisper-large-v3"
TEXT_MODEL_NAME = "microsoft/Phi-3-mini-4k-instruct"
BATCH_SIZE = 8

pipe = pipeline(
    task="automatic-speech-recognition",
    model=AUDIO_MODEL_NAME,
    chunk_length_s=30,
    device=device,
)
client = InferenceClient()


def transcribe(audio_input):
    """Function to convert audio to text."""
    if audio_input is None:
        raise gr.Error("No audio file submitted!")

    output = pipe(
        audio_input,
        batch_size=BATCH_SIZE,
        generate_kwargs={"task": "transcribe"},
        return_timestamps=True
    )
    return output["text"]


def organize_text(meeting_transcript):
    messages = build_messages(meeting_transcript)
    response = client.chat_completion(
        messages, model=TEXT_MODEL_NAME, max_tokens=250, seed=430
    )
    return response.choices[0].message.content


def build_messages(meeting_transcript) -> list:
    system_input = "You are an assitant that organizes meeting minutes."
    user_input = """Take this raw meeting transcript and return an organized version.
    Here is the transcript:
    {meeting_transcript}
    """.format(meeting_transcript=meeting_transcript)

    messages = [
        {"role": "system", "content": system_input},
        {"role": "user", "content": user_input},
    ]
    return messages

def meeting_transcript_tool(audio_input):
    meeting_text = transcribe(audio_input)
    organized_text = organize_text(meeting_text)
    return organized_text


full_demo = gr.Interface(
    fn=meeting_transcript_tool,
    inputs=gr.Audio(type="filepath"),
    outputs=gr.Textbox(show_copy_button=True),
    title="Meeting Transcript Tool (Recipe from the Enterprise Hub Cookbook)",
)
full_demo.launch()