Spaces:
Sleeping
Sleeping
File size: 2,611 Bytes
15678e0 82da87b 15678e0 82da87b 15678e0 82da87b 15678e0 82da87b 15678e0 a26be94 15678e0 82da87b 15678e0 82da87b a26be94 15678e0 82da87b 15678e0 82da87b a26be94 419f944 a26be94 15678e0 82da87b 15678e0 419f944 15678e0 419f944 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
# Load both translation models from Hugging Face
# English to Moroccan Arabic (Darija)
tokenizer_eng_to_darija = AutoTokenizer.from_pretrained("Saidtaoussi/AraT5_Darija_to_MSA")
model_eng_to_darija = AutoModelForSeq2SeqLM.from_pretrained("Saidtaoussi/AraT5_Darija_to_MSA")
# Moroccan Arabic (Darija) to Modern Standard Arabic (MSA)
tokenizer_darija_to_msa = AutoTokenizer.from_pretrained("lachkarsalim/Helsinki-translation-English_Moroccan-Arabic")
model_darija_to_msa = AutoModelForSeq2SeqLM.from_pretrained("lachkarsalim/Helsinki-translation-English_Moroccan-Arabic")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
translation_choice: str,
):
# Ensure there's no empty input
if not message.strip():
return "Error: Please enter a valid text to translate."
# Initialize the response variable
response = ""
# Translate based on the user's choice
try:
if translation_choice == "Moroccan Arabic to MSA":
# Translate Moroccan Arabic (Darija) to Modern Standard Arabic
inputs = tokenizer_darija_to_msa(message, return_tensors="pt", padding=True)
outputs = model_darija_to_msa.generate(inputs["input_ids"], num_beams=5, max_length=max_tokens, early_stopping=True)
response = tokenizer_darija_to_msa.decode(outputs[0], skip_special_tokens=True)
elif translation_choice == "English to Moroccan Arabic":
# Translate English to Moroccan Arabic (Darija)
inputs = tokenizer_eng_to_darija(message, return_tensors="pt", padding=True)
outputs = model_eng_to_darija.generate(inputs["input_ids"], num_beams=5, max_length=max_tokens, early_stopping=True)
response = tokenizer_eng_to_darija.decode(outputs[0], skip_special_tokens=True)
except Exception as e:
response = f"Error occurred: {str(e)}"
return response
# Gradio interface setup without pre-filled system message
demo = gr.Interface(
fn=respond,
inputs=[
gr.Textbox(value="", label="Enter Your Text", placeholder="Type your sentence here..."),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Dropdown(
label="Choose Translation Direction",
choices=["English to Moroccan Arabic", "Moroccan Arabic to MSA"],
value="English to Moroccan Arabic"
),
],
outputs="text"
)
# Launch the interface
demo.launch()
|