import os
os.system("pip install git+https://github.com/openai/whisper.git")
import gradio as gr
import whisper
from flask import Flask, jsonify, request
import requests
import numpy as np
import streamlit as st




app = Flask(__name__)

@app.route("/")
def indexApi():
    return jsonify({"output": "okay"})

@app.route("/run", methods=['POST'])
def runApi():
    audio_url = request.form.get("audio_url")
    # key = request.form.get("key")
    # model = request.form.get("model")
    print(audio_url)

    if (modelSelection == None):
        modelSelection = "small"
    model = whisper.load_model(modelSelection)
    print(model)

    # # reject if key not the same 
    # apiKey = st.secrets["Api-Key"]
    # if apiKey != key:
    #     return jsonify({
    #         "image_url": image_url,
    #         "model": model,
    #         "result": "Invalid API Key",
    #     }), 400


    response = requests.get(audio_url)

    if response.status_code == requests.codes.ok:
        # Only attempt to save the file if the request was successful
        with open("audio.mp3", "wb") as f:
            f.write(response.content)
      
    else:
        return jsonify({
            "result": "Unable to save file, status code:  {response.status_code}" ,
        }), 400

    # arr = np.asarray(bytearray(response.content), dtype=np.uint8)
    result = model.transcribe("audio.mp3")

    return jsonify({
        "audio_url": audio_url,
        "model": model,
        "result": result["text"],
    })

if __name__ == "__main__":
    app.run(host="0.0.0.0", port=7860)
        
# def inference(audio):
#     audio = whisper.load_audio(audio)
#     audio = whisper.pad_or_trim(audio)
    
#     mel = whisper.log_mel_spectrogram(audio).to(model.device)
    
#     _, probs = model.detect_language(mel)
    
#     options = whisper.DecodingOptions(fp16 = False)
#     result = whisper.decode(model, mel, options)
    
#     # print(result.text)
#     return result.text, gr.update(visible=True), gr.update(visible=True), gr.update(visible=True)




# css = """
#         .gradio-container {
#             font-family: 'IBM Plex Sans', sans-serif;
#         }
#         .gr-button {
#             color: white;
#             border-color: black;
#             background: black;
#         }
#         input[type='range'] {
#             accent-color: black;
#         }
#         .dark input[type='range'] {
#             accent-color: #dfdfdf;
#         }
#         .container {
#             max-width: 730px;
#             margin: auto;
#             padding-top: 1.5rem;
#         }
     
#         .details:hover {
#             text-decoration: underline;
#         }
#         .gr-button {
#             white-space: nowrap;
#         }
#         .gr-button:focus {
#             border-color: rgb(147 197 253 / var(--tw-border-opacity));
#             outline: none;
#             box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
#             --tw-border-opacity: 1;
#             --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
#             --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color);
#             --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity));
#             --tw-ring-opacity: .5;
#         }
#         .footer {
#             margin-bottom: 45px;
#             margin-top: 35px;
#             text-align: center;
#             border-bottom: 1px solid #e5e5e5;
#         }
#         .footer>p {
#             font-size: .8rem;
#             display: inline-block;
#             padding: 0 10px;
#             transform: translateY(10px);
#             background: white;
#         }
#         .dark .footer {
#             border-color: #303030;
#         }
#         .dark .footer>p {
#             background: #0b0f19;
#         }
#         .prompt h4{
#             margin: 1.25em 0 .25em 0;
#             font-weight: bold;
#             font-size: 115%;
#         }
#         .animate-spin {
#             animation: spin 1s linear infinite;
#         }
#         @keyframes spin {
#             from {
#                 transform: rotate(0deg);
#             }
#             to {
#                 transform: rotate(360deg);
#             }
#         }
#         #share-btn-container {
#             display: flex; margin-top: 1.5rem !important; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem;
#         }
#         #share-btn {
#             all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important;
#         }
#         #share-btn * {
#             all: unset;
#         }
# """

# block = gr.Blocks(css=css)



# with block:
#     gr.HTML(
#         """
#             <div style="text-align: center; max-width: 650px; margin: 0 auto;">
#               <div
#                 style="
#                   display: inline-flex;
#                   align-items: center;
#                   gap: 0.8rem;
#                   font-size: 1.75rem;
#                 "
#               >
#                 <svg
#                   width="0.65em"
#                   height="0.65em"
#                   viewBox="0 0 115 115"
#                   fill="none"
#                   xmlns="http://www.w3.org/2000/svg"
#                 >
#                   <rect width="23" height="23" fill="white"></rect>
#                   <rect y="69" width="23" height="23" fill="white"></rect>
#                   <rect x="23" width="23" height="23" fill="#AEAEAE"></rect>
#                   <rect x="23" y="69" width="23" height="23" fill="#AEAEAE"></rect>
#                   <rect x="46" width="23" height="23" fill="white"></rect>
#                   <rect x="46" y="69" width="23" height="23" fill="white"></rect>
#                   <rect x="69" width="23" height="23" fill="black"></rect>
#                   <rect x="69" y="69" width="23" height="23" fill="black"></rect>
#                   <rect x="92" width="23" height="23" fill="#D9D9D9"></rect>
#                   <rect x="92" y="69" width="23" height="23" fill="#AEAEAE"></rect>
#                   <rect x="115" y="46" width="23" height="23" fill="white"></rect>
#                   <rect x="115" y="115" width="23" height="23" fill="white"></rect>
#                   <rect x="115" y="69" width="23" height="23" fill="#D9D9D9"></rect>
#                   <rect x="92" y="46" width="23" height="23" fill="#AEAEAE"></rect>
#                   <rect x="92" y="115" width="23" height="23" fill="#AEAEAE"></rect>
#                   <rect x="92" y="69" width="23" height="23" fill="white"></rect>
#                   <rect x="69" y="46" width="23" height="23" fill="white"></rect>
#                   <rect x="69" y="115" width="23" height="23" fill="white"></rect>
#                   <rect x="69" y="69" width="23" height="23" fill="#D9D9D9"></rect>
#                   <rect x="46" y="46" width="23" height="23" fill="black"></rect>
#                   <rect x="46" y="115" width="23" height="23" fill="black"></rect>
#                   <rect x="46" y="69" width="23" height="23" fill="black"></rect>
#                   <rect x="23" y="46" width="23" height="23" fill="#D9D9D9"></rect>
#                   <rect x="23" y="115" width="23" height="23" fill="#AEAEAE"></rect>
#                   <rect x="23" y="69" width="23" height="23" fill="black"></rect>
#                 </svg>
#                 <h1 style="font-weight: 900; margin-bottom: 7px;">
#                   Whisper
#                 </h1>
#               </div>
#               <p style="margin-bottom: 10px; font-size: 94%">
#                 Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification. This demo cuts audio after around 30 secs.
#               </p>
#                <p>You can skip the queue by using google colab for the space: <a href="https://colab.research.google.com/drive/1WJ98KHgZxFGrHiMm4TyWZllSew_Af_ff?usp=sharing"><img data-canonical-src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" src="https://camo.githubusercontent.com/84f0493939e0c4de4e6dbe113251b4bfb5353e57134ffd9fcab6b8714514d4d1/68747470733a2f2f636f6c61622e72657365617263682e676f6f676c652e636f6d2f6173736574732f636f6c61622d62616467652e737667"></a></p>
#             </div>
#         """
#     )
#     with gr.Group():
#         with gr.Box():
#             with gr.Row().style(mobile_collapse=False, equal_height=True):
#                 audio = gr.Audio(
#                     label="Input Audio",
#                     show_label=False,
#                     source="microphone",
#                     type="filepath"
#                 )

#                 btn = gr.Button("Transcribe")
#         text = gr.Textbox(show_label=False, elem_id="result-textarea")
#         with gr.Group(elem_id="share-btn-container"):
#             community_icon = gr.HTML(community_icon_html, visible=False)
#             loading_icon = gr.HTML(loading_icon_html, visible=False)
#             share_button = gr.Button("Share to community", elem_id="share-btn", visible=False)
        


        
#         btn.click(inference, inputs=[audio], outputs=[text, community_icon, loading_icon, share_button])
#         share_button.click(None, [], [], _js=share_js)
 
#         gr.HTML('''
#         <div class="footer">
#                     <p>Model by <a href="https://github.com/openai/whisper" style="text-decoration: underline;" target="_blank">OpenAI</a> - Gradio Demo by 🤗 Hugging Face
#                     </p>
#         </div>
#         ''')

# block.launch()