File size: 2,030 Bytes
76b06b6 b912ba6 122790b b912ba6 a6fc19e e22e364 dd34156 122790b b912ba6 dc03f7a b912ba6 2c29438 111af19 0b60e87 dc03f7a 0b60e87 dd34156 02a14aa b912ba6 122790b dd34156 dc03f7a dd34156 |
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 |
import streamlit as st
from transformers import MarianTokenizer, MarianMTModel
import torch
LANGUAGES = {
"en": ("English", "English"), "fr": ("Français", "French"), "es": ("Español", "Spanish"),
"de": ("Deutsch", "German"), "hi": ("हिन्दी", "Hindi"), "zh": ("中文", "Chinese"),
"ar": ("العربية", "Arabic"), "ru": ("Русский", "Russian"), "ja": ("日本語", "Japanese")
}
@st.cache_resource
def _load_default_model():
model_name = "Helsinki-NLP/opus-mt-en-hi"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
return tokenizer, model
@st.cache_resource
def load_model(source_lang, target_lang):
try:
if source_lang == target_lang:
return _load_default_model()
# Try direct model first
model_name = f"Helsinki-NLP/opus-mt-{source_lang}-{target_lang}"
try:
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
return tokenizer, model
except Exception:
# Pivot through English for non-English pairs
if source_lang != "en" and target_lang != "en":
en_to_target = load_model("en", target_lang)
source_to_en = load_model(source_lang, "en")
return source_to_en if source_lang == "en" else en_to_target
return _load_default_model()
except Exception:
return _load_default_model()
def translate(text, source_lang, target_lang):
if not text:
return ""
try:
tokenizer, model = load_model(source_lang, target_lang)
inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=500)
with torch.no_grad():
translated = model.generate(**inputs, max_length=500, num_beams=2, early_stopping=True)
return tokenizer.decode(translated[0], skip_special_tokens=True)
except Exception:
return text |