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

# Correct way to load all available tokenizers as per the provided usage information
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(text):
    results = []
    for name, tokenizer in tokenizers.items():
        tokens = tokenizer.tokenize(text)
        encoded_output = tokenizer.encode(text, add_special_tokens=True)
        decoded_text = tokenizer.decode(encoded_output)
        # Collect each tokenizer's results
        results.append((name, tokens, encoded_output, decoded_text))
    return results

# Correctly use Gradio's components for inputs and outputs
inputs_component = gr.components.Textbox(lines=2, placeholder="Enter Arabic text here...", label="Input Text")
outputs_component = gr.components.Table(label="Results", headers=["Tokenizer", "Tokens", "Encoded Output", "Decoded Text"])

# 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()