app.py

import gradio as gr
from processing import run

# from utils import hf_login
# hf_login()

from huggingface_hub import login
import os

hf_token = os.getenv("HF_Token")
login(hf_token)


MODEL_OPTIONS = ["openai/whisper-tiny.en", "facebook/s2t-medium-librispeech-asr"]
DATASET_OPTIONS = ["Common Voice", "VoxPopuli", "OWN Recoding/Sample"]


# def eval(data_subset:str, model_1:str, model_2:str, own_audio, own_transcription:str)->str:

#     print("OWN AUDIO: ", type(own_audio), own_audio)

#     wer_result_1, wer_result_2, references, transcriptions1, transcriptions2 = run(data_subset, model_1, model_2, own_audio, own_transcription)

#     results_md = f"""#### {model_1} 
#     - WER Score: {wer_result_1}
    
#     #### {model_2} 
#     - WER Score: {wer_result_2}"""

#     # Create the bar plot
#     fig = go.Figure(
#         data=[
#             go.Bar(x=[f"{model_1}"], y=[wer_result_1]),
#             go.Bar(x=[f"{model_2}"], y=[wer_result_2]),
#         ]
#     )

#     # Update the layout for better visualization
#     fig.update_layout(
#         title="Comparison of Two Models",
#         xaxis_title="Models",
#         yaxis_title="Value",
#         barmode="group",
#     )

#     return results_md, fig

def get_card(selected_model:str)->str:

    with open("cards.txt", "r") as f:
        cards = f.read()
    
    cards = cards.split("@@")
    for card in cards:
        if "ID: "+selected_model in card:
            return card

    return "Unknown Model"

def is_own(selected_option):
    if selected_option == "OWN Recoding/Sample":
        return gr.update(visible=True), gr.update(visible=True)
    else:
        return gr.update(visible=False), gr.update(visible=False)

with gr.Blocks() as demo:


    gr.Markdown('# <p style="text-align: center;">ASR Model Comparison 💬</p>')
    gr.Markdown("-------")


    gr.Markdown("""### Welcome to ASR Model Comparison Hub! 🎉

Hey there, and welcome to an app designed just for developers like you, who are passionate about pushing the boundaries of Automatic Speech Recognition (ASR) technology!

Here, you can easily compare different ASR models by selecting a dataset and choosing two models from the dropdown to see how they stack up against each other. If you're feeling creative, go ahead and select 'OWN' as your dataset option to upload your own audio file or record something new right in the app. Don’t forget to provide a transcription, and the app will handle the rest!

ASR Model Comparison Hub uses the Word Error Rate (WER) ⬇️ (the lower the better) metric to give you a clear picture of each model's performance. And hey, don't miss out on checking the **Amazing Leaderboard** where you can see how a wide range of models have been evaluated—[Check it out here](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard).

Happy experimenting and comparing! 🚀""")

    

    with gr.Row():
        with gr.Column(scale=1):
            pass
        with gr.Column(scale=5):
            data_subset = gr.Radio(
                value="Common Voice",
                choices=DATASET_OPTIONS,
                label="Data subset / Own Sample",
            )
            own_audio = gr.Audio(visible=False)
            own_transcription = gr.TextArea(lines=2, visible=False)
            data_subset.change(is_own, inputs=[data_subset], outputs=[own_audio, own_transcription])
        with gr.Column(scale=1):
            pass


    with gr.Row():

        with gr.Column(scale=1):
            model_1 = gr.Dropdown(
                choices=MODEL_OPTIONS,
                label="Select Model"
            )
            model_1_card = gr.Markdown("")

        with gr.Column(scale=1):
            model_2 = gr.Dropdown(
                choices=MODEL_OPTIONS,
                label="Select Model"
            )
            model_2_card = gr.Markdown("")


        model_1.change(get_card, inputs=model_1, outputs=model_1_card)
        model_2.change(get_card, inputs=model_2, outputs=model_2_card)


    eval_btn = gr.Button(
        value="Evaluate",
        variant="primary",
        size="sm")
    
    gr.Markdown('## <p style="text-align: center;">Results</p>')
    results_md = gr.Markdown("")
    results_plot = gr.Plot(show_label=False)
    eval_btn.click(run, [data_subset, model_1, model_2, own_audio, own_transcription], [results_md, results_plot])

demo.launch(debug=True)