import streamlit as st
import requests
from transformers import pipeline


# Function to send the audio file to the Hugging Face Whisper API
def query(file_data, my_key):
    API_URL = "https://api-inference.huggingface.co/models/openai/whisper-large-v3-turbo"
    headers = {"Authorization": f"Bearer {my_key}"}
    
    try:
        response = requests.post(API_URL, headers=headers, files={"file": file_data})
        if response.status_code == 200:
            return response.json()
        else:
            return {"error": f"API returned status code {response.status_code}: {response.text}"}
    except requests.exceptions.RequestException as e:
        return {"error": str(e)}

# Streamlit UI elements
st.title("Whisper Transcription App")
st.write("Upload one or more .wav, .mp3, or .flac audio files, and get the transcription.")

# Get the user's Hugging Face API key
my_key = st.text_input("Enter your Hugging Face API Key", type="password")

# File uploader for audio files
uploaded_files = st.file_uploader("Choose audio file(s)", type=["mp3", "wav", "flac"], accept_multiple_files=True)

if my_key and uploaded_files:  # Proceed only if the API key is provided and files are uploaded
    st.write("Processing your files...")
    results = {}
    
    for uploaded_file in uploaded_files:
        try:
            # Read the file data
            file_data = uploaded_file.read()
            
            # Query the API
            st.write(f"Transcribing: {uploaded_file.name}")
            result = query(file_data, my_key)
            
            # Store the result
            results[uploaded_file.name] = result
        except Exception as e:
            st.write(f"Error processing {uploaded_file.name}: {str(e)}")
    
    # Display results
    for file, result in results.items():
        st.write(f"**Results for {file}:**")
        if "error" in result:
            st.error(result["error"])
        else:
            st.json(result)