initial commit

README.md

@@ -1,10 +1,10 @@
 ---
-title: Bangla English Translation BanglaT5
-emoji: 🚀
-colorFrom: purple
-colorTo: pink
+title: BanglishToBanglaTranslation
+emoji: 🏢
+colorFrom: gray
+colorTo: purple
 sdk: streamlit
-sdk_version: 1.37.1
+sdk_version: 1.37.0
 app_file: app.py
 pinned: false
 license: apache-2.0

app.py

@@ -0,0 +1,51 @@
+# Import necessary libraries
+import streamlit as st
+import numpy as np
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+from normalizer import normalize
+
+# Set the page configuration
+st.set_page_config(
+    page_title="Bengalai to English Translator App",  # Title of the app displayed in the browser tab
+    page_icon=":shield:",  # Path to a favicon or emoji to be displayed in the browser tab
+    initial_sidebar_state="auto"  # Initial state of the sidebar ("auto", "expanded", or "collapsed")
+)
+
+
+# Load custom CSS styling
+with open("assets/style.css") as f:
+    st.markdown("<style>{}</style>".format(f.read()), unsafe_allow_html=True)
+
+# Function to load the pre-trained model
+# @st.cache_data(experimental_allow_widgets=False)
+def get_model():
+    tokenizer = AutoTokenizer.from_pretrained("kazalbrur/BanglaEnglishTokenizerBanglaT5", use_fast=True) # Set legacy=False
+    model = AutoModelForSeq2SeqLM.from_pretrained("kazalbrur/BanglaEnglishTranslationBanglaT5") # Set legacy=False
+    return tokenizer, model
+
+
+# Load the tokenizer and model
+tokenizer, model = get_model()
+
+
+# Add a header to the Streamlit app
+st.header("Benglai to English Translator")
+
+# Add placeholder text with custom CSS styling
+st.markdown("<span style='color:black'>Enter your Banglish text here</span>", unsafe_allow_html=True)
+
+# Text area for user input with label and height set to 250
+user_input = st.text_area("Enter your Banglish text here", "", height=250, label_visibility="collapsed")
+
+# Button for submitting the input
+submit_button = st.button("Translate")
+
+# Perform prediction when user input is provided and the submit button is clicked
+if user_input and submit_button:
+    input_ids = tokenizer(normalize(user_input), padding=True, truncation=True, max_length=128, return_tensors="pt").input_ids
+    generated_tokens = model.generate(input_ids, max_new_tokens=128)  # Set max_new_tokens to control generation length
+    decoded_tokens = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]
+    st.write(f"<span style='color:black'>Bangla Translation: {decoded_tokens}</span>", unsafe_allow_html=True)
+
+
+

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,7 @@
+git+https://github.com/csebuetnlp/normalizer
+numpy==1.26.4
+streamlit==1.31.1
+torch
+sentencepiece
+transformers[sentencepiece]
+transformers==4.38.2