Spaces:
Sleeping
Sleeping
File size: 4,651 Bytes
279ed8e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 |
import os
import sys
import codecs
import torch
from transformers import M2M100ForConditionalGeneration, NllbTokenizerFast
def translate_text(text, model, tokenizer, src_lang, target_lang="eng_Latn"):
"""
Translates a single text string.
"""
try:
tokenizer.src_lang = src_lang
inputs = tokenizer(text, return_tensors="pt")
generated_tokens = model.generate(
**inputs,
forced_bos_token_id=tokenizer.vocab[target_lang],
max_length=512
)
translated_text = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]
return translated_text
except Exception as e:
return f"An error occurred during translation: {e}"
def main():
"""
Main function to load the model and run a test translation.
"""
# Reconfigure stdout to handle UTF-8 encoding
sys.stdout = codecs.getwriter('utf-8')(sys.stdout.buffer)
# --- Configuration ---
script_dir = os.path.dirname(os.path.abspath(__file__))
nepali_model_path = os.path.join(script_dir, "models", "nllb-finetuned-nepali-en")
# --- Model Loading ---
print("Loading Nepali model and tokenizer...")
try:
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
nepali_model = M2M100ForConditionalGeneration.from_pretrained(nepali_model_path).to(device)
nepali_tokenizer = NllbTokenizerFast.from_pretrained(nepali_model_path)
print("Nepali model and tokenizer loaded successfully.")
except Exception as e:
print(f"Error loading Nepali model or tokenizer: {e}")
return
# --- Nepali Translation ---
nepali_sentences = [
"जडान बिन्दु थप्नुहोस्",
"स्टिकी नोट आयात पूरा भयो",
"मोनोस्पेस १२",
"पानी जेट पम्पमा दुईवटा भित्रिने र एउटा बाहिरिने पाइप हुन्छन् र एक भित्र अर्को सिद्धान्त अनुरूप दुईवटा पाइप हुन्छन् । पानीको प्रविष्टिमा एउटा पानी जेटले केही ठूलो पाइपमा पूरा चापले टुटीबाट बाहिर फाल्दछ । यस्तो तरिकाले पानी जेटले वायू वा तरललाई दोस्रो प्रविष्टिबाट टाढा पुर्याउदछ । ड्रिफ्टिङ तरलमा ऋणात्मक चापको कारणले यस्तो हुन्छ । त्यसैले यो हाइड्रोडायनमिक विरोधाभाषको एउटा अनुप्रयोग हो । यसले ड्रिफ्टिङ तरल नजिकका वस्तु टाढा फाल्नुको साटोमा सोस्ने कुरा बताउदछ ।",
"वस्तुको परिवर्तन बचत गर्नुहोस् ।"
"तिमीलाई कस्तो छ" ,
"तिमी को हौ",
"कति बज्यो"
]
print("\n--- Nepali to English Translation Analysis ---")
for sentence in nepali_sentences:
print(f"\nOriginal (ne): {sentence}")
translated_text = translate_text(sentence, nepali_model, nepali_tokenizer, src_lang="nep_Npan")
print(f"Translated (en): {translated_text}")
# --- Sinhala Translation ---
# NOTE: No fine-tuned model for sinhala was found. Using the baseline model for now.
print("\n\n--- Sinhala to English Translation Analysis ---")
sinhala_sentences = [
"ඩෝසන්මිස් දුරකථනයෙන් ඩෝසන්මිස් කවුද සර්",
"කවුද ඩෝසන් නැතුව ඉන්නේ ඔව් සර්",
"ඔබ එය උත්සාහ කරන්න සර්",
"කොහොමද වැඩේ හරිද ඔව් සර්ට ස්තුතියි",
"ඔව්, හරි, ස්තුතියි රත්තරං",
]
for sentence in sinhala_sentences:
print(f"\nOriginal (si): {sentence}")
translated_text = translate_text(sentence, nepali_model, nepali_tokenizer, src_lang="sin_Sinh")
print(f"Translated (en): {translated_text}")
if __name__ == "__main__":
main()
|