app.py

# ============================================================
# Aplikasi Translasi Jawa -> Indonesia & Inggris + Evaluasi
# MODEL: facebook/m2m100_418M
# METRIK: BLEU + ROUGE-L + METEOR
# ============================================================

import torch
import gradio as gr
import sacrebleu
import nltk
import torch

from rouge import Rouge
from nltk.translate.meteor_score import meteor_score
from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer

print("=== APP STARTED ===")

# ============================================================
# Download NLTK resources (for METEOR)
# ============================================================

nltk.download("wordnet")
nltk.download("omw-1.4")

# ============================================================
# Load Model & Tokenizer
# ============================================================

MODEL_NAME = "facebook/m2m100_418M"

tokenizer = M2M100Tokenizer.from_pretrained(MODEL_NAME)
model = M2M100ForConditionalGeneration.from_pretrained(MODEL_NAME)

device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

print("Model loaded on:", device)

# ============================================================
# Translasi Function
# ============================================================

def translate_jawa(text):
    if not text.strip():
        return "", ""

    tokenizer.src_lang = "jv"

    inputs = tokenizer(
        text,
        return_tensors="pt",
        padding=True,
        truncation=True,
        max_length=512
    ).to(device)

    # Indonesia
    gen_id = model.generate(
        **inputs,
        forced_bos_token_id=tokenizer.get_lang_id("id"),
        max_length=512
    )

    # English
    gen_en = model.generate(
        **inputs,
        forced_bos_token_id=tokenizer.get_lang_id("en"),
        max_length=512
    )

    id_text = tokenizer.batch_decode(
        gen_id,
        skip_special_tokens=True
    )[0]

    en_text = tokenizer.batch_decode(
        gen_en,
        skip_special_tokens=True
    )[0]

    return id_text, en_text

# ============================================================
# Evaluasi Function (BLEU + ROUGE-L + METEOR)
# ============================================================

def evaluate_translation(jawa, ref_id, ref_en):
    pred_id, pred_en = translate_jawa(jawa)

    # BLEU (Indonesia)
    bleu = sacrebleu.corpus_bleu(
        [pred_id],
        [[ref_id]]
    ).score

    # ROUGE-L (Indonesia)
    rouge = Rouge()
    rouge_l = rouge.get_scores(
        pred_id,
        ref_id
    )[0]["rouge-l"]["f"]

    # METEOR (Indonesia)
    meteor = meteor_score(
        [ref_id.split()],
        pred_id.split()
    )

    return (
        pred_id,
        pred_en,
        f"{bleu:.2f}",
        f"{rouge_l:.4f}",
        f"{meteor:.4f}"
    )

# ============================================================
# Gradio UI
# ============================================================

with gr.Blocks(title="Jawa → Indonesia & English Translator") as demo:
    gr.Markdown("## 🈶 Translasi Bahasa Jawa + Evaluasi")
    gr.Markdown(
        "Model: **facebook/m2m100_418M**  \n"
        "Output: Indonesia & English  \n"
        "Evaluasi: **BLEU · ROUGE-L · METEOR**"
    )

    with gr.Tab("🔤 Translasi"):
        inp = gr.Textbox(lines=5, label="Teks Bahasa Jawa")
        out_id = gr.Textbox(lines=3, label="Terjemahan Indonesia")
        out_en = gr.Textbox(lines=3, label="Terjemahan English")
        btn = gr.Button("Terjemahkan")

        btn.click(
            fn=translate_jawa,
            inputs=inp,
            outputs=[out_id, out_en]
        )

    with gr.Tab("📊 Evaluasi"):
        eval_jawa = gr.Textbox(lines=4, label="Teks Jawa")
        ref_id = gr.Textbox(lines=2, label="Referensi Indonesia")
        ref_en = gr.Textbox(lines=2, label="Referensi English (opsional)")

        pred_id = gr.Textbox(label="Prediksi Indonesia")
        pred_en = gr.Textbox(label="Prediksi English")
        bleu = gr.Textbox(label="BLEU Score")
        rouge_l = gr.Textbox(label="ROUGE-L F1")
        meteor = gr.Textbox(label="METEOR Score")

        eval_btn = gr.Button("Evaluasi")

        eval_btn.click(
            fn=evaluate_translation,
            inputs=[eval_jawa, ref_id, ref_en],
            outputs=[pred_id, pred_en, bleu, rouge_l, meteor]
        )

# ============================================================
# Launch App
# ============================================================

if __name__ == "__main__":
    print("=== LAUNCHING GRADIO ===")
    demo.launch(
        server_name="0.0.0.0",
        server_port=7860,
        share=False
    )