app.py

from gradio import Interface
import gradio as gr
import aranizer
from aranizer import aranizer_bpe50k, aranizer_bpe64k, aranizer_bpe86k, aranizer_sp32k, aranizer_sp50k, aranizer_sp64k, aranizer_sp86k

# List of available tokenizers and a dictionary to load them
tokenizer_options = [
    "aranizer_bpe50k", "aranizer_bpe64k", "aranizer_bpe86k",
    "aranizer_sp32k", "aranizer_sp50k", "aranizer_sp64k", "aranizer_sp86k"
]

tokenizers = {
    "aranizer_bpe50k": aranizer_bpe50k.get_tokenizer,
    "aranizer_bpe64k": aranizer_bpe64k.get_tokenizer,
    "aranizer_bpe86k": aranizer_bpe86k.get_tokenizer,
    "aranizer_sp32k": aranizer_sp32k.get_tokenizer,
    "aranizer_sp50k": aranizer_sp50k.get_tokenizer,
    "aranizer_sp64k": aranizer_sp64k.get_tokenizer,
    "aranizer_sp86k": aranizer_sp86k.get_tokenizer,
}

def compare_tokenizers(tokenizer_name, text):
    # Load the selected tokenizer
    tokenizer = tokenizers[tokenizer_name]()
    tokens = tokenizer.tokenize(text)
    encoded_output = tokenizer.encode(text, add_special_tokens=True)
    decoded_text = tokenizer.decode(encoded_output)
    
    # Prepare the results to be displayed
    results = [(tokenizer_name, tokens, encoded_output, decoded_text)]
    return results

# Define the Gradio interface components with a dropdown for model selection
inputs_component = [
    gr.Dropdown(choices=tokenizer_options, label="Select Tokenizer"),
    gr.Textbox(lines=2, placeholder="Enter Arabic text here...", label="Input Text")
]
outputs_component = gr.Dataframe(headers=["Tokenizer", "Tokens", "Encoded Output", "Decoded Text"], label="Results")

# Setting up the interface
iface = Interface(fn=compare_tokenizers, inputs=inputs_component, outputs=outputs_component, title="AraNizer Tokenizer Comparison")

# Launching the Gradio app
iface.launch()