Spaces:
Build error
Build error
Bengali Tokenizer app
Browse files- app.py +110 -0
- bengali_bpe_tokenizer.json +1696 -0
- bengali_bpe_tokenizer.py +183 -0
app.py
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
import json
|
| 3 |
+
from bengali_bpe_tokenizer import BengaliBPETokenizer
|
| 4 |
+
import random
|
| 5 |
+
import colorsys
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
def generate_distinct_colors(n):
|
| 9 |
+
"""Generate n visually distinct colors"""
|
| 10 |
+
colors = []
|
| 11 |
+
for i in range(n):
|
| 12 |
+
hue = i / n
|
| 13 |
+
saturation = 0.7
|
| 14 |
+
value = 0.9
|
| 15 |
+
rgb = colorsys.hsv_to_rgb(hue, saturation, value)
|
| 16 |
+
hex_color = "#{:02x}{:02x}{:02x}".format(
|
| 17 |
+
int(rgb[0] * 255), int(rgb[1] * 255), int(rgb[2] * 255)
|
| 18 |
+
)
|
| 19 |
+
colors.append(hex_color)
|
| 20 |
+
return colors
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
def load_tokenizer():
|
| 24 |
+
try:
|
| 25 |
+
return BengaliBPETokenizer.load("bengali_bpe_tokenizer.json")
|
| 26 |
+
except:
|
| 27 |
+
# If no saved tokenizer found, create a new one
|
| 28 |
+
return BengaliBPETokenizer(vocab_size=5000)
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
def tokenize_text(text):
|
| 32 |
+
tokenizer = load_tokenizer()
|
| 33 |
+
|
| 34 |
+
# Get token IDs and their corresponding text
|
| 35 |
+
token_ids = tokenizer.encode(text)
|
| 36 |
+
tokens = []
|
| 37 |
+
current_pos = 0
|
| 38 |
+
|
| 39 |
+
# Process text to get token spans
|
| 40 |
+
words = [list(text)]
|
| 41 |
+
for pair, merged in tokenizer.merges.items():
|
| 42 |
+
words = tokenizer._merge_vocab(words, pair)
|
| 43 |
+
|
| 44 |
+
# Extract final tokens
|
| 45 |
+
final_tokens = []
|
| 46 |
+
for word in words:
|
| 47 |
+
final_tokens.extend(word)
|
| 48 |
+
|
| 49 |
+
# Generate colors for tokens
|
| 50 |
+
colors = generate_distinct_colors(len(tokenizer.vocab))
|
| 51 |
+
color_map = {
|
| 52 |
+
token_id: color for token_id, color in zip(tokenizer.vocab.values(), colors)
|
| 53 |
+
}
|
| 54 |
+
|
| 55 |
+
# Create highlighted HTML
|
| 56 |
+
html_parts = []
|
| 57 |
+
token_list = []
|
| 58 |
+
|
| 59 |
+
for i, token in enumerate(final_tokens):
|
| 60 |
+
token_id = tokenizer.vocab.get(token, tokenizer.special_tokens["<UNK>"])
|
| 61 |
+
color = color_map[token_id]
|
| 62 |
+
html_parts.append(f'<span style="background-color: {color}">{token}</span>')
|
| 63 |
+
token_list.append(f"{token} ({token_id})")
|
| 64 |
+
|
| 65 |
+
highlighted_text = "".join(html_parts)
|
| 66 |
+
|
| 67 |
+
# Calculate compression ratio
|
| 68 |
+
compression_ratio = len(text) / len(token_ids) if len(token_ids) > 0 else 0
|
| 69 |
+
|
| 70 |
+
return (
|
| 71 |
+
len(token_ids), # Token count
|
| 72 |
+
compression_ratio, # Compression ratio
|
| 73 |
+
highlighted_text, # Highlighted text
|
| 74 |
+
"\n".join(token_list), # Token list
|
| 75 |
+
)
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
custom_css = """
|
| 79 |
+
.token-highlight {
|
| 80 |
+
border-radius: 3px;
|
| 81 |
+
margin: 0 1px;
|
| 82 |
+
}
|
| 83 |
+
.container {
|
| 84 |
+
max-width: 1200px;
|
| 85 |
+
margin: 0 auto;
|
| 86 |
+
}
|
| 87 |
+
"""
|
| 88 |
+
|
| 89 |
+
with gr.Blocks(css=custom_css) as demo:
|
| 90 |
+
gr.Markdown("# Bengali BPE Tokenizer")
|
| 91 |
+
|
| 92 |
+
with gr.Row():
|
| 93 |
+
with gr.Column(scale=1):
|
| 94 |
+
input_text = gr.Textbox(
|
| 95 |
+
label="Input Text", placeholder="Enter Bengali text here...", lines=10
|
| 96 |
+
)
|
| 97 |
+
|
| 98 |
+
with gr.Column(scale=1):
|
| 99 |
+
token_count = gr.Number(label="Token Count")
|
| 100 |
+
compression_ratio = gr.Number(label="Compression Ratio")
|
| 101 |
+
highlighted_output = gr.HTML(label="Tokenized Text")
|
| 102 |
+
token_list = gr.Textbox(label="Token List", lines=10)
|
| 103 |
+
|
| 104 |
+
input_text.change(
|
| 105 |
+
fn=tokenize_text,
|
| 106 |
+
inputs=[input_text],
|
| 107 |
+
outputs=[token_count, compression_ratio, highlighted_output, token_list],
|
| 108 |
+
)
|
| 109 |
+
|
| 110 |
+
demo.launch()
|
bengali_bpe_tokenizer.json
ADDED
|
@@ -0,0 +1,1696 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vocab": {
|
| 3 |
+
"<PAD>": 0,
|
| 4 |
+
"<UNK>": 1,
|
| 5 |
+
"<BOS>": 2,
|
| 6 |
+
"<EOS>": 3,
|
| 7 |
+
"\t": 4,
|
| 8 |
+
"\n": 5,
|
| 9 |
+
" ": 6,
|
| 10 |
+
" অ": 7,
|
| 11 |
+
" অক": 8,
|
| 12 |
+
" অকৃত": 9,
|
| 13 |
+
" অকৃত্র": 10,
|
| 14 |
+
" অকৃত্রিম": 11,
|
| 15 |
+
" অগ": 12,
|
| 16 |
+
" অঙ্গ": 13,
|
| 17 |
+
" অজ": 14,
|
| 18 |
+
" অজিত": 15,
|
| 19 |
+
" অজিতক": 16,
|
| 20 |
+
" অজিতকুম": 17,
|
| 21 |
+
" অজিতকুমার": 18,
|
| 22 |
+
" অত": 19,
|
| 23 |
+
" অতি": 20,
|
| 24 |
+
" অতিথ": 21,
|
| 25 |
+
" অতিথি": 22,
|
| 26 |
+
" অধ": 23,
|
| 27 |
+
" অধিকার": 24,
|
| 28 |
+
" অধ্যা": 25,
|
| 29 |
+
" অধ্যাপনার": 26,
|
| 30 |
+
" অন": 27,
|
| 31 |
+
" অনু": 28,
|
| 32 |
+
" অনে": 29,
|
| 33 |
+
" অনেক": 30,
|
| 34 |
+
" অব": 31,
|
| 35 |
+
" অবকাশ": 32,
|
| 36 |
+
" অভ": 33,
|
| 37 |
+
" অভাব": 34,
|
| 38 |
+
" অর্": 35,
|
| 39 |
+
" অল্প": 36,
|
| 40 |
+
" অস": 37,
|
| 41 |
+
" অসা": 38,
|
| 42 |
+
" আ": 39,
|
| 43 |
+
" আত": 40,
|
| 44 |
+
" আত্ম": 41,
|
| 45 |
+
" আত্মদান": 42,
|
| 46 |
+
" আদর্শ": 43,
|
| 47 |
+
" আদর্শের": 44,
|
| 48 |
+
" আন": 45,
|
| 49 |
+
" আনন্দের": 46,
|
| 50 |
+
" আপ": 47,
|
| 51 |
+
" আপন": 48,
|
| 52 |
+
" আপনাকে": 49,
|
| 53 |
+
" আপনার": 50,
|
| 54 |
+
" আম": 51,
|
| 55 |
+
" আমা": 52,
|
| 56 |
+
" আমাকে": 53,
|
| 57 |
+
" আমাদের": 54,
|
| 58 |
+
" আমার": 55,
|
| 59 |
+
" আমি": 56,
|
| 60 |
+
" আর": 57,
|
| 61 |
+
" আরম্ভ": 58,
|
| 62 |
+
" আর্": 59,
|
| 63 |
+
" আর্থ": 60,
|
| 64 |
+
" আর্থিক": 61,
|
| 65 |
+
" আশ্রম": 62,
|
| 66 |
+
" আশ্রমের": 63,
|
| 67 |
+
" আস": 64,
|
| 68 |
+
" আস্ব": 65,
|
| 69 |
+
" আস্বাদ": 66,
|
| 70 |
+
" আহ": 67,
|
| 71 |
+
" আহার": 68,
|
| 72 |
+
" ই": 69,
|
| 73 |
+
" ইং": 70,
|
| 74 |
+
" ইংরে": 71,
|
| 75 |
+
" ইংরেজ": 72,
|
| 76 |
+
" ইংরেজি": 73,
|
| 77 |
+
" উ": 74,
|
| 78 |
+
" উচ": 75,
|
| 79 |
+
" উচ্চ": 76,
|
| 80 |
+
" উত্ত": 77,
|
| 81 |
+
" উত্তর": 78,
|
| 82 |
+
" উপ": 79,
|
| 83 |
+
" উপরে": 80,
|
| 84 |
+
" উপল": 81,
|
| 85 |
+
" উপলক্ষে": 82,
|
| 86 |
+
" উপা": 83,
|
| 87 |
+
" উপায়ে": 84,
|
| 88 |
+
" এ": 85,
|
| 89 |
+
" এই": 86,
|
| 90 |
+
" এক": 87,
|
| 91 |
+
" একজন": 88,
|
| 92 |
+
" একটা": 89,
|
| 93 |
+
" একটি": 90,
|
| 94 |
+
" একত": 91,
|
| 95 |
+
" এব": 92,
|
| 96 |
+
" এবং": 93,
|
| 97 |
+
" এম": 94,
|
| 98 |
+
" এমন": 95,
|
| 99 |
+
" এসে": 96,
|
| 100 |
+
" এসেছিলেন": 97,
|
| 101 |
+
" ও": 98,
|
| 102 |
+
" ক": 99,
|
| 103 |
+
" কখন": 100,
|
| 104 |
+
" কখনো": 101,
|
| 105 |
+
" কথা": 102,
|
| 106 |
+
" কদ": 103,
|
| 107 |
+
" কর": 104,
|
| 108 |
+
" করত": 105,
|
| 109 |
+
" করতুম": 106,
|
| 110 |
+
" করতে": 107,
|
| 111 |
+
" করবার": 108,
|
| 112 |
+
" করা": 109,
|
| 113 |
+
" করে": 110,
|
| 114 |
+
" করেছিলেন": 111,
|
| 115 |
+
" কর্ম": 112,
|
| 116 |
+
" কা": 113,
|
| 117 |
+
" কাছ": 114,
|
| 118 |
+
" কাছে": 115,
|
| 119 |
+
" কাজ": 116,
|
| 120 |
+
" কাজে": 117,
|
| 121 |
+
" কার": 118,
|
| 122 |
+
" কারণ": 119,
|
| 123 |
+
" কালের": 120,
|
| 124 |
+
" কিন্ত": 121,
|
| 125 |
+
" কিন্তু": 122,
|
| 126 |
+
" কৃপণতা": 123,
|
| 127 |
+
" কে": 124,
|
| 128 |
+
" কেব": 125,
|
| 129 |
+
" কেবল": 126,
|
| 130 |
+
" কো": 127,
|
| 131 |
+
" কোথা": 128,
|
| 132 |
+
" কোথাও": 129,
|
| 133 |
+
" কোনো": 130,
|
| 134 |
+
" ক্র": 131,
|
| 135 |
+
" ক্ষ": 132,
|
| 136 |
+
" কয়েক": 133,
|
| 137 |
+
" খ": 134,
|
| 138 |
+
" গ": 135,
|
| 139 |
+
" গা": 136,
|
| 140 |
+
" গাছের": 137,
|
| 141 |
+
" গে": 138,
|
| 142 |
+
" গেছে": 139,
|
| 143 |
+
" গেলেন": 140,
|
| 144 |
+
" ঘ": 141,
|
| 145 |
+
" ঘরে": 142,
|
| 146 |
+
" চ": 143,
|
| 147 |
+
" চল": 144,
|
| 148 |
+
" চলতে": 145,
|
| 149 |
+
" চে": 146,
|
| 150 |
+
" চেষ্ট": 147,
|
| 151 |
+
" চেষ্টা": 148,
|
| 152 |
+
" ছ": 149,
|
| 153 |
+
" ছাত্র": 150,
|
| 154 |
+
" ছাত্রকে": 151,
|
| 155 |
+
" ছাত্রদের": 152,
|
| 156 |
+
" ছাত্রের": 153,
|
| 157 |
+
" ছায়": 154,
|
| 158 |
+
" ছিল": 155,
|
| 159 |
+
" ছিলেন": 156,
|
| 160 |
+
" ছে": 157,
|
| 161 |
+
" ছেলে": 158,
|
| 162 |
+
" ছেলেদের": 159,
|
| 163 |
+
" ছোট": 160,
|
| 164 |
+
" ছোটো": 161,
|
| 165 |
+
" জ": 162,
|
| 166 |
+
" জগ": 163,
|
| 167 |
+
" জগদান": 164,
|
| 168 |
+
" জগদানন্দ": 165,
|
| 169 |
+
" জন": 166,
|
| 170 |
+
" জন্য": 167,
|
| 171 |
+
" জন্যে": 168,
|
| 172 |
+
" জম": 169,
|
| 173 |
+
" জমি": 170,
|
| 174 |
+
" জমিদার": 171,
|
| 175 |
+
" জা": 172,
|
| 176 |
+
" জান": 173,
|
| 177 |
+
" জাম": 174,
|
| 178 |
+
" জীব": 175,
|
| 179 |
+
" জুগ": 176,
|
| 180 |
+
" জুগিয়ে": 177,
|
| 181 |
+
" জ্": 178,
|
| 182 |
+
" জ্ঞ": 179,
|
| 183 |
+
" জ্ঞানের": 180,
|
| 184 |
+
" ত": 181,
|
| 185 |
+
" তখন": 182,
|
| 186 |
+
" তখনো": 183,
|
| 187 |
+
" তব": 184,
|
| 188 |
+
" তবুও": 185,
|
| 189 |
+
" তবে": 186,
|
| 190 |
+
" তলায়": 187,
|
| 191 |
+
" তা": 188,
|
| 192 |
+
" তাঁ": 189,
|
| 193 |
+
" তাঁকে": 190,
|
| 194 |
+
" তাঁদের": 191,
|
| 195 |
+
" তাঁর": 192,
|
| 196 |
+
" তাতে": 193,
|
| 197 |
+
" তাদের": 194,
|
| 198 |
+
" তার": 195,
|
| 199 |
+
" তারই": 196,
|
| 200 |
+
" তারা": 197,
|
| 201 |
+
" তাল": 198,
|
| 202 |
+
" তিনি": 199,
|
| 203 |
+
" থা": 200,
|
| 204 |
+
" থাক": 201,
|
| 205 |
+
" থাকা": 202,
|
| 206 |
+
" থাকে": 203,
|
| 207 |
+
" থে": 204,
|
| 208 |
+
" থেকে": 205,
|
| 209 |
+
" দ": 206,
|
| 210 |
+
" দক্ষিণ": 207,
|
| 211 |
+
" দান": 208,
|
| 212 |
+
" দারি": 209,
|
| 213 |
+
" দারিদ্র": 210,
|
| 214 |
+
" দিকে": 211,
|
| 215 |
+
" দিত": 212,
|
| 216 |
+
" দিতে": 213,
|
| 217 |
+
" দিতেন": 214,
|
| 218 |
+
" দিল": 215,
|
| 219 |
+
" দিলেন": 216,
|
| 220 |
+
" দিয়ে": 217,
|
| 221 |
+
" দিয়েছিলেন": 218,
|
| 222 |
+
" দীর্": 219,
|
| 223 |
+
" দীর্ঘ": 220,
|
| 224 |
+
" দু": 221,
|
| 225 |
+
" দুটি": 222,
|
| 226 |
+
" দে": 223,
|
| 227 |
+
" দেখ": 224,
|
| 228 |
+
" দেখা": 225,
|
| 229 |
+
" দেখে": 226,
|
| 230 |
+
" দো": 227,
|
| 231 |
+
" দ্ব": 228,
|
| 232 |
+
" দ্বার": 229,
|
| 233 |
+
" দ্বারা": 230,
|
| 234 |
+
" ধ": 231,
|
| 235 |
+
" ন": 232,
|
| 236 |
+
" নত": 233,
|
| 237 |
+
" নতুন": 234,
|
| 238 |
+
" না": 235,
|
| 239 |
+
" নান": 236,
|
| 240 |
+
" নানা": 237,
|
| 241 |
+
" নি": 238,
|
| 242 |
+
" নিত": 239,
|
| 243 |
+
" নিদর্শ": 240,
|
| 244 |
+
" নিদর্শন": 241,
|
| 245 |
+
" নির": 242,
|
| 246 |
+
" নির্": 243,
|
| 247 |
+
" নিয়ে": 244,
|
| 248 |
+
" নিয়েছিলেন": 245,
|
| 249 |
+
" নে": 246,
|
| 250 |
+
" নেই": 247,
|
| 251 |
+
" নয়": 248,
|
| 252 |
+
" প": 249,
|
| 253 |
+
" পক্ষে": 250,
|
| 254 |
+
" পদ": 251,
|
| 255 |
+
" পর": 252,
|
| 256 |
+
" পরি": 253,
|
| 257 |
+
" পরিচ": 254,
|
| 258 |
+
" পরিচয়": 255,
|
| 259 |
+
" পরিধ": 256,
|
| 260 |
+
" পরিমাণ": 257,
|
| 261 |
+
" পরী": 258,
|
| 262 |
+
" পরীক্ষ": 259,
|
| 263 |
+
" পরীক্ষা": 260,
|
| 264 |
+
" পরে": 261,
|
| 265 |
+
" পর্যন্ত": 262,
|
| 266 |
+
" পা": 263,
|
| 267 |
+
" পাকা": 264,
|
| 268 |
+
" পাঠ": 265,
|
| 269 |
+
" পাত": 266,
|
| 270 |
+
" পাতায়": 267,
|
| 271 |
+
" পার": 268,
|
| 272 |
+
" পারতেন": 269,
|
| 273 |
+
" পিছ": 270,
|
| 274 |
+
" পুর": 271,
|
| 275 |
+
" পূর্": 272,
|
| 276 |
+
" পে": 273,
|
| 277 |
+
" পেয়ে": 274,
|
| 278 |
+
" পেয়েছিলেন": 275,
|
| 279 |
+
" প্র": 276,
|
| 280 |
+
" প্রচ": 277,
|
| 281 |
+
" প্রত": 278,
|
| 282 |
+
" প্রতি": 279,
|
| 283 |
+
" প্রথ": 280,
|
| 284 |
+
" প্রথম": 281,
|
| 285 |
+
" প্রব": 282,
|
| 286 |
+
" প্রবন্ধ": 283,
|
| 287 |
+
" প্রস": 284,
|
| 288 |
+
" প্রা": 285,
|
| 289 |
+
" প্রাচীন": 286,
|
| 290 |
+
" প্রান্ত": 287,
|
| 291 |
+
" প্রের": 288,
|
| 292 |
+
" প্রয়": 289,
|
| 293 |
+
" প্রয়ো": 290,
|
| 294 |
+
" প্রয়োজন": 291,
|
| 295 |
+
" পড়": 292,
|
| 296 |
+
" পড়া": 293,
|
| 297 |
+
" পড়াবার": 294,
|
| 298 |
+
" পড়ে": 295,
|
| 299 |
+
" ব": 296,
|
| 300 |
+
" বন্ধ": 297,
|
| 301 |
+
" বন্ধু": 298,
|
| 302 |
+
" বর্তমান": 299,
|
| 303 |
+
" বল": 300,
|
| 304 |
+
" বললেন": 301,
|
| 305 |
+
" বস্ত": 302,
|
| 306 |
+
" বস্তু": 303,
|
| 307 |
+
" বস্তুত": 304,
|
| 308 |
+
" বহ": 305,
|
| 309 |
+
" বহু": 306,
|
| 310 |
+
" বা": 307,
|
| 311 |
+
" বাঁ": 308,
|
| 312 |
+
" বাঁধান": 309,
|
| 313 |
+
" বাঁধানো": 310,
|
| 314 |
+
" বাল": 311,
|
| 315 |
+
" বালক": 312,
|
| 316 |
+
" বালকদের": 313,
|
| 317 |
+
" বাড়ি": 314,
|
| 318 |
+
" বি": 315,
|
| 319 |
+
" বিক": 316,
|
| 320 |
+
" বিকাশ": 317,
|
| 321 |
+
" বিদ": 318,
|
| 322 |
+
" বিদায়": 319,
|
| 323 |
+
" বিশ": 320,
|
| 324 |
+
" বিশ্ব": 321,
|
| 325 |
+
" বিশ্ববি": 322,
|
| 326 |
+
" বিশ্ববিদ": 323,
|
| 327 |
+
" বিশ্ববিদ্যালয়ের": 324,
|
| 328 |
+
" বিষ": 325,
|
| 329 |
+
" বিস্ত": 326,
|
| 330 |
+
" বিস্তার": 327,
|
| 331 |
+
" বৃ": 328,
|
| 332 |
+
" বে": 329,
|
| 333 |
+
" বেত": 330,
|
| 334 |
+
" বেতন": 331,
|
| 335 |
+
" বেদ": 332,
|
| 336 |
+
" বেদনা": 333,
|
| 337 |
+
" বৈ": 334,
|
| 338 |
+
" ব্য": 335,
|
| 339 |
+
" ব্রহ": 336,
|
| 340 |
+
" ব্রহ্ম": 337,
|
| 341 |
+
" ব্রহ্মব": 338,
|
| 342 |
+
" ব্রহ্মবান": 339,
|
| 343 |
+
" ব্রহ্মবান্ধ": 340,
|
| 344 |
+
" ব্রহ্মবান্ধব": 341,
|
| 345 |
+
" বড়": 342,
|
| 346 |
+
" বড়ো": 343,
|
| 347 |
+
" বয়": 344,
|
| 348 |
+
" বয়স": 345,
|
| 349 |
+
" বয়সের": 346,
|
| 350 |
+
" ভ": 347,
|
| 351 |
+
" ভা": 348,
|
| 352 |
+
" ভার": 349,
|
| 353 |
+
" ভাষ": 350,
|
| 354 |
+
" ভিত": 351,
|
| 355 |
+
" ভিতরে": 352,
|
| 356 |
+
" ভুল": 353,
|
| 357 |
+
" ভুলতে": 354,
|
| 358 |
+
" ম": 355,
|
| 359 |
+
" মত": 356,
|
| 360 |
+
" মতো": 357,
|
| 361 |
+
" মধ": 358,
|
| 362 |
+
" মধ্যে": 359,
|
| 363 |
+
" মনে": 360,
|
| 364 |
+
" মনের": 361,
|
| 365 |
+
" মা": 362,
|
| 366 |
+
" মাঠ": 363,
|
| 367 |
+
" মাস": 364,
|
| 368 |
+
" মু": 365,
|
| 369 |
+
" মুখ": 366,
|
| 370 |
+
" মৃত": 367,
|
| 371 |
+
" মৃত্য": 368,
|
| 372 |
+
" মৃত্যু": 369,
|
| 373 |
+
" য": 370,
|
| 374 |
+
" যথ": 371,
|
| 375 |
+
" যথার্থ": 372,
|
| 376 |
+
" যদ": 373,
|
| 377 |
+
" যদি": 374,
|
| 378 |
+
" যদিও": 375,
|
| 379 |
+
" যা": 376,
|
| 380 |
+
" যার": 377,
|
| 381 |
+
" যারা": 378,
|
| 382 |
+
" যে": 379,
|
| 383 |
+
" যোগ": 380,
|
| 384 |
+
" যোগ্য": 381,
|
| 385 |
+
" র": 382,
|
| 386 |
+
" রক্ষ": 383,
|
| 387 |
+
" রক্ষা": 384,
|
| 388 |
+
" রক্ষার": 385,
|
| 389 |
+
" রস": 386,
|
| 390 |
+
" রা": 387,
|
| 391 |
+
" রাখ": 388,
|
| 392 |
+
" রাখতে": 389,
|
| 393 |
+
" রাজ": 390,
|
| 394 |
+
" রাস্ত": 391,
|
| 395 |
+
" রূপ": 392,
|
| 396 |
+
" রোগ": 393,
|
| 397 |
+
" ল": 394,
|
| 398 |
+
" লা": 395,
|
| 399 |
+
" লে": 396,
|
| 400 |
+
" লো": 397,
|
| 401 |
+
" লোক": 398,
|
| 402 |
+
" শ": 399,
|
| 403 |
+
" শান্ত": 400,
|
| 404 |
+
" শান্তিন": 401,
|
| 405 |
+
" শান্তিনিকে": 402,
|
| 406 |
+
" শান্তিনিকেত": 403,
|
| 407 |
+
" শান্তিনিকেতনের": 404,
|
| 408 |
+
" শাল": 405,
|
| 409 |
+
" শাস": 406,
|
| 410 |
+
" শাসন": 407,
|
| 411 |
+
" শিক্ষ": 408,
|
| 412 |
+
" শিক্ষক": 409,
|
| 413 |
+
" শিক্ষকতা": 410,
|
| 414 |
+
" শিক্ষকের": 411,
|
| 415 |
+
" শিক্ষা": 412,
|
| 416 |
+
" শিক্ষার": 413,
|
| 417 |
+
" শেষ": 414,
|
| 418 |
+
" শ্র": 415,
|
| 419 |
+
" শ্রদ্ধ": 416,
|
| 420 |
+
" শ্রদ্ধার": 417,
|
| 421 |
+
" স": 418,
|
| 422 |
+
" সং": 419,
|
| 423 |
+
" সংক": 420,
|
| 424 |
+
" সংকল্প": 421,
|
| 425 |
+
" সংকীর্ণ": 422,
|
| 426 |
+
" সংগ": 423,
|
| 427 |
+
" সঙ্গে": 424,
|
| 428 |
+
" সঞ্চ": 425,
|
| 429 |
+
" সত": 426,
|
| 430 |
+
" সতীশ": 427,
|
| 431 |
+
" সতীশের": 428,
|
| 432 |
+
" সত্য": 429,
|
| 433 |
+
" সব": 430,
|
| 434 |
+
" সম": 431,
|
| 435 |
+
" সমস্ত": 432,
|
| 436 |
+
" সমা": 433,
|
| 437 |
+
" সম্প": 434,
|
| 438 |
+
" সম্পূর্": 435,
|
| 439 |
+
" সম্ব": 436,
|
| 440 |
+
" সম্বন্ধ": 437,
|
| 441 |
+
" সময়ে": 438,
|
| 442 |
+
" সর্": 439,
|
| 443 |
+
" সর্ব": 440,
|
| 444 |
+
" সর্বত": 441,
|
| 445 |
+
" সর্বতো": 442,
|
| 446 |
+
" সর্বতোভাবে": 443,
|
| 447 |
+
" সহ": 444,
|
| 448 |
+
" সহজ": 445,
|
| 449 |
+
" সা": 446,
|
| 450 |
+
" সাধ": 447,
|
| 451 |
+
" সাধক": 448,
|
| 452 |
+
" সাধনা": 449,
|
| 453 |
+
" সাধনাক্ষে": 450,
|
| 454 |
+
" সাধনাক্ষেত্রে": 451,
|
| 455 |
+
" সাম": 452,
|
| 456 |
+
" সামনে": 453,
|
| 457 |
+
" সাহিত": 454,
|
| 458 |
+
" সাহিত্য": 455,
|
| 459 |
+
" সাহিত্যে": 456,
|
| 460 |
+
" সাহিত্যের": 457,
|
| 461 |
+
" সী": 458,
|
| 462 |
+
" সীমান": 459,
|
| 463 |
+
" সীমানায়": 460,
|
| 464 |
+
" সুগ": 461,
|
| 465 |
+
" সুগভীর": 462,
|
| 466 |
+
" সৃষ্ট": 463,
|
| 467 |
+
" সৃষ্টিকার": 464,
|
| 468 |
+
" সৃষ্টিকার্যে": 465,
|
| 469 |
+
" সৃষ্টির": 466,
|
| 470 |
+
" সে": 467,
|
| 471 |
+
" সেই": 468,
|
| 472 |
+
" সেখান": 469,
|
| 473 |
+
" সেখানে": 470,
|
| 474 |
+
" স্": 471,
|
| 475 |
+
" স্থ": 472,
|
| 476 |
+
" স্ব": 473,
|
| 477 |
+
" স্বভাব": 474,
|
| 478 |
+
" স্বভাবের": 475,
|
| 479 |
+
" স্বীকার": 476,
|
| 480 |
+
" হ": 477,
|
| 481 |
+
" হত": 478,
|
| 482 |
+
" হবে": 479,
|
| 483 |
+
" হাতে": 480,
|
| 484 |
+
" হয়": 481,
|
| 485 |
+
" হয়ে": 482,
|
| 486 |
+
" হয়েছিল": 483,
|
| 487 |
+
" হয়েছে": 484,
|
| 488 |
+
" ২": 485,
|
| 489 |
+
"ঀ": 486,
|
| 490 |
+
"ঁ": 487,
|
| 491 |
+
"ঁদের": 488,
|
| 492 |
+
"ং": 489,
|
| 493 |
+
"ঃ": 490,
|
| 494 |
+
"": 491,
|
| 495 |
+
"অ": 492,
|
| 496 |
+
"আ": 493,
|
| 497 |
+
"আশ্রমের": 494,
|
| 498 |
+
"ই": 495,
|
| 499 |
+
"ইন": 496,
|
| 500 |
+
"ঈ": 497,
|
| 501 |
+
"উ": 498,
|
| 502 |
+
"ঊ": 499,
|
| 503 |
+
"ঋ": 500,
|
| 504 |
+
"ঌ": 501,
|
| 505 |
+
"": 502,
|
| 506 |
+
"": 503,
|
| 507 |
+
"এ": 504,
|
| 508 |
+
"এই": 505,
|
| 509 |
+
"এক": 506,
|
| 510 |
+
"ঐ": 507,
|
| 511 |
+
"": 508,
|
| 512 |
+
"": 509,
|
| 513 |
+
"ও": 510,
|
| 514 |
+
"ওয়": 511,
|
| 515 |
+
"ঔ": 512,
|
| 516 |
+
"ক": 513,
|
| 517 |
+
"কল": 514,
|
| 518 |
+
"কা": 515,
|
| 519 |
+
"কার": 516,
|
| 520 |
+
"কার্যে": 517,
|
| 521 |
+
"কাল": 518,
|
| 522 |
+
"কালে": 519,
|
| 523 |
+
"কালের": 520,
|
| 524 |
+
"কাশ": 521,
|
| 525 |
+
"কিছ": 522,
|
| 526 |
+
"কিছু": 523,
|
| 527 |
+
"কে": 524,
|
| 528 |
+
"কের": 525,
|
| 529 |
+
"ক্ত": 526,
|
| 530 |
+
"ক্তি": 527,
|
| 531 |
+
"ক্ষ": 528,
|
| 532 |
+
"ক্ষা": 529,
|
| 533 |
+
"ক্ষি": 530,
|
| 534 |
+
"ক্ষিণ": 531,
|
| 535 |
+
"ক্ষে": 532,
|
| 536 |
+
"খ": 533,
|
| 537 |
+
"খন": 534,
|
| 538 |
+
"খা": 535,
|
| 539 |
+
"খান": 536,
|
| 540 |
+
"খানে": 537,
|
| 541 |
+
"খে": 538,
|
| 542 |
+
"গ": 539,
|
| 543 |
+
"গত": 540,
|
| 544 |
+
"গা": 541,
|
| 545 |
+
"গের": 542,
|
| 546 |
+
"ঘ": 543,
|
| 547 |
+
"ঙ": 544,
|
| 548 |
+
"ঙ্": 545,
|
| 549 |
+
"ঙ্গ": 546,
|
| 550 |
+
"ঙ্গে": 547,
|
| 551 |
+
"চ": 548,
|
| 552 |
+
"চন্দ": 549,
|
| 553 |
+
"চন্দ্র": 550,
|
| 554 |
+
"চর": 551,
|
| 555 |
+
"চা": 552,
|
| 556 |
+
"চিত": 553,
|
| 557 |
+
"চিত্র": 554,
|
| 558 |
+
"চীন": 555,
|
| 559 |
+
"ছ": 556,
|
| 560 |
+
"ছি": 557,
|
| 561 |
+
"ছিল": 558,
|
| 562 |
+
"ছিলুম": 559,
|
| 563 |
+
"ছিলেন": 560,
|
| 564 |
+
"ছে": 561,
|
| 565 |
+
"ছেন": 562,
|
| 566 |
+
"ছের": 563,
|
| 567 |
+
"জ": 564,
|
| 568 |
+
"জন": 565,
|
| 569 |
+
"জনের": 566,
|
| 570 |
+
"জে": 567,
|
| 571 |
+
"জের": 568,
|
| 572 |
+
"জ্": 569,
|
| 573 |
+
"জ্জ": 570,
|
| 574 |
+
"জ্জ্ব": 571,
|
| 575 |
+
"জ্জ্বল": 572,
|
| 576 |
+
"জ্ঞ": 573,
|
| 577 |
+
"ঝ": 574,
|
| 578 |
+
"ঞ": 575,
|
| 579 |
+
"ঞ্": 576,
|
| 580 |
+
"ঞ্চ": 577,
|
| 581 |
+
"ঞ্জ": 578,
|
| 582 |
+
"ঞ্জল": 579,
|
| 583 |
+
"ট": 580,
|
| 584 |
+
"টা": 581,
|
| 585 |
+
"টি": 582,
|
| 586 |
+
"ঠ": 583,
|
| 587 |
+
"ঠা": 584,
|
| 588 |
+
"ড": 585,
|
| 589 |
+
"ঢ": 586,
|
| 590 |
+
"ণ": 587,
|
| 591 |
+
"ণতা": 588,
|
| 592 |
+
"ণে": 589,
|
| 593 |
+
"ণ্": 590,
|
| 594 |
+
"ণ্ড": 591,
|
| 595 |
+
"ণ্ডার": 592,
|
| 596 |
+
"ণ্���": 593,
|
| 597 |
+
"ত": 594,
|
| 598 |
+
"তলা": 595,
|
| 599 |
+
"তা": 596,
|
| 600 |
+
"তার": 597,
|
| 601 |
+
"তায়": 598,
|
| 602 |
+
"তি": 599,
|
| 603 |
+
"তুম": 600,
|
| 604 |
+
"তে": 601,
|
| 605 |
+
"তেন": 602,
|
| 606 |
+
"ত্ত": 603,
|
| 607 |
+
"ত্র": 604,
|
| 608 |
+
"ত্রে": 605,
|
| 609 |
+
"থ": 606,
|
| 610 |
+
"থা": 607,
|
| 611 |
+
"থায়": 608,
|
| 612 |
+
"থে": 609,
|
| 613 |
+
"দ": 610,
|
| 614 |
+
"দর্শ": 611,
|
| 615 |
+
"দান": 612,
|
| 616 |
+
"দার": 613,
|
| 617 |
+
"দিন": 614,
|
| 618 |
+
"দিনের": 615,
|
| 619 |
+
"দের": 616,
|
| 620 |
+
"দ্ধ": 617,
|
| 621 |
+
"দ্র": 618,
|
| 622 |
+
"ধ": 619,
|
| 623 |
+
"ধান": 620,
|
| 624 |
+
"ধ্য": 621,
|
| 625 |
+
"ন": 622,
|
| 626 |
+
"নকে": 623,
|
| 627 |
+
"না": 624,
|
| 628 |
+
"নাকে": 625,
|
| 629 |
+
"নি": 626,
|
| 630 |
+
"নে": 627,
|
| 631 |
+
"নের": 628,
|
| 632 |
+
"নো": 629,
|
| 633 |
+
"ন্": 630,
|
| 634 |
+
"ন্ত": 631,
|
| 635 |
+
"ন্ত্র": 632,
|
| 636 |
+
"ন্দ": 633,
|
| 637 |
+
"ন্দের": 634,
|
| 638 |
+
"ন্ধ": 635,
|
| 639 |
+
"ন্ন": 636,
|
| 640 |
+
"ন্য": 637,
|
| 641 |
+
"": 638,
|
| 642 |
+
"প": 639,
|
| 643 |
+
"পন": 640,
|
| 644 |
+
"পনার": 641,
|
| 645 |
+
"পর": 642,
|
| 646 |
+
"পরী": 643,
|
| 647 |
+
"পা": 644,
|
| 648 |
+
"পুণ": 645,
|
| 649 |
+
"প্ত": 646,
|
| 650 |
+
"প্র": 647,
|
| 651 |
+
"ফ": 648,
|
| 652 |
+
"ব": 649,
|
| 653 |
+
"বা": 650,
|
| 654 |
+
"বাঁ": 651,
|
| 655 |
+
"বাগ": 652,
|
| 656 |
+
"বার": 653,
|
| 657 |
+
"বি": 654,
|
| 658 |
+
"বিত": 655,
|
| 659 |
+
"বে": 656,
|
| 660 |
+
"বেশ": 657,
|
| 661 |
+
"ভ": 658,
|
| 662 |
+
"ভব": 659,
|
| 663 |
+
"ভা": 660,
|
| 664 |
+
"ভাব": 661,
|
| 665 |
+
"ভাবে": 662,
|
| 666 |
+
"ভীর": 663,
|
| 667 |
+
"ম": 664,
|
| 668 |
+
"মতা": 665,
|
| 669 |
+
"মা": 666,
|
| 670 |
+
"মাণ": 667,
|
| 671 |
+
"মাত্র": 668,
|
| 672 |
+
"মান": 669,
|
| 673 |
+
"মান্য": 670,
|
| 674 |
+
"মার": 671,
|
| 675 |
+
"ম্ব": 672,
|
| 676 |
+
"ম্ভ": 673,
|
| 677 |
+
"য": 674,
|
| 678 |
+
"যুক্ত": 675,
|
| 679 |
+
"যোগ": 676,
|
| 680 |
+
"র": 677,
|
| 681 |
+
"রণ": 678,
|
| 682 |
+
"রা": 679,
|
| 683 |
+
"রাজ": 680,
|
| 684 |
+
"রূপ": 681,
|
| 685 |
+
"রূপে": 682,
|
| 686 |
+
"রে": 683,
|
| 687 |
+
"রের": 684,
|
| 688 |
+
"র্": 685,
|
| 689 |
+
"র্জন": 686,
|
| 690 |
+
"র্ত": 687,
|
| 691 |
+
"র্তমান": 688,
|
| 692 |
+
"র্ম": 689,
|
| 693 |
+
"র্শ": 690,
|
| 694 |
+
"": 691,
|
| 695 |
+
"ল": 692,
|
| 696 |
+
"লা": 693,
|
| 697 |
+
"লার": 694,
|
| 698 |
+
"লায়": 695,
|
| 699 |
+
"লুম": 696,
|
| 700 |
+
"লে": 697,
|
| 701 |
+
"লেন": 698,
|
| 702 |
+
"লেম": 699,
|
| 703 |
+
"লের": 700,
|
| 704 |
+
"ল্প": 701,
|
| 705 |
+
"": 702,
|
| 706 |
+
"": 703,
|
| 707 |
+
"": 704,
|
| 708 |
+
"শ": 705,
|
| 709 |
+
"শি": 706,
|
| 710 |
+
"শিক্ষ": 707,
|
| 711 |
+
"শ্চ": 708,
|
| 712 |
+
"শ্চিম": 709,
|
| 713 |
+
"শ্র": 710,
|
| 714 |
+
"শ্রম": 711,
|
| 715 |
+
"শ্রমের": 712,
|
| 716 |
+
"শ্রে": 713,
|
| 717 |
+
"শ্রেণ": 714,
|
| 718 |
+
"ষ": 715,
|
| 719 |
+
"ষ্": 716,
|
| 720 |
+
"ষ্ট": 717,
|
| 721 |
+
"ষ্ঠ": 718,
|
| 722 |
+
"ষ্য": 719,
|
| 723 |
+
"স": 720,
|
| 724 |
+
"সা": 721,
|
| 725 |
+
"সার": 722,
|
| 726 |
+
"সে": 723,
|
| 727 |
+
"স্ট": 724,
|
| 728 |
+
"স্ত": 725,
|
| 729 |
+
"স্ব": 726,
|
| 730 |
+
"স্য": 727,
|
| 731 |
+
"হ": 728,
|
| 732 |
+
"হিত": 729,
|
| 733 |
+
"হে": 730,
|
| 734 |
+
"": 731,
|
| 735 |
+
"": 732,
|
| 736 |
+
"়": 733,
|
| 737 |
+
"ঽ": 734,
|
| 738 |
+
"া": 735,
|
| 739 |
+
"াই": 736,
|
| 740 |
+
"াক": 737,
|
| 741 |
+
"াত": 738,
|
| 742 |
+
"াতে": 739,
|
| 743 |
+
"াত্র": 740,
|
| 744 |
+
"াদ": 741,
|
| 745 |
+
"ান": 742,
|
| 746 |
+
"ানের": 743,
|
| 747 |
+
"ান্ত": 744,
|
| 748 |
+
"ার": 745,
|
| 749 |
+
"ারি": 746,
|
| 750 |
+
"ার্থ": 747,
|
| 751 |
+
"াল": 748,
|
| 752 |
+
"ালী": 749,
|
| 753 |
+
"াশ": 750,
|
| 754 |
+
"াস": 751,
|
| 755 |
+
"ায়": 752,
|
| 756 |
+
"ি": 753,
|
| 757 |
+
"িক": 754,
|
| 758 |
+
"িকার": 755,
|
| 759 |
+
"িকে": 756,
|
| 760 |
+
"িক্ষ": 757,
|
| 761 |
+
"িগ": 758,
|
| 762 |
+
"িছ": 759,
|
| 763 |
+
"িত": 760,
|
| 764 |
+
"িতে": 761,
|
| 765 |
+
"িন": 762,
|
| 766 |
+
"িনি": 763,
|
| 767 |
+
"িন্ত": 764,
|
| 768 |
+
"িম": 765,
|
| 769 |
+
"ির": 766,
|
| 770 |
+
"িল": 767,
|
| 771 |
+
"িষ্ট": 768,
|
| 772 |
+
"িয়": 769,
|
| 773 |
+
"িয়ে": 770,
|
| 774 |
+
"ী": 771,
|
| 775 |
+
"ীকার": 772,
|
| 776 |
+
"ীন": 773,
|
| 777 |
+
"ীব": 774,
|
| 778 |
+
"ীর": 775,
|
| 779 |
+
"ীর্": 776,
|
| 780 |
+
"ীর্ণ": 777,
|
| 781 |
+
"ীশ": 778,
|
| 782 |
+
"ু": 779,
|
| 783 |
+
"ুও": 780,
|
| 784 |
+
"ুক্ত": 781,
|
| 785 |
+
"ুগ": 782,
|
| 786 |
+
"ুণ": 783,
|
| 787 |
+
"ুন": 784,
|
| 788 |
+
"ুব": 785,
|
| 789 |
+
"ুম": 786,
|
| 790 |
+
"ুর": 787,
|
| 791 |
+
"ুল": 788,
|
| 792 |
+
"ুলে": 789,
|
| 793 |
+
"ূ": 790,
|
| 794 |
+
"ূপ": 791,
|
| 795 |
+
"ূর্": 792,
|
| 796 |
+
"ৃ": 793,
|
| 797 |
+
"ৃত": 794,
|
| 798 |
+
"ৃত্তির": 795,
|
| 799 |
+
"ৃপ": 796,
|
| 800 |
+
"ৃপণতা": 797,
|
| 801 |
+
"ৃষ্ট": 798,
|
| 802 |
+
"ৄ": 799,
|
| 803 |
+
"": 800,
|
| 804 |
+
"": 801,
|
| 805 |
+
"ে": 802,
|
| 806 |
+
"েন": 803,
|
| 807 |
+
"েন্": 804,
|
| 808 |
+
"েন্দ্র": 805,
|
| 809 |
+
"েন্দ্রনা": 806,
|
| 810 |
+
"েন্দ্রনাথ": 807,
|
| 811 |
+
"ের": 808,
|
| 812 |
+
"েষ": 809,
|
| 813 |
+
"ৈ": 810,
|
| 814 |
+
"": 811,
|
| 815 |
+
"": 812,
|
| 816 |
+
"ো": 813,
|
| 817 |
+
"োগ": 814,
|
| 818 |
+
"োচ": 815,
|
| 819 |
+
"োট": 816,
|
| 820 |
+
"োধ": 817,
|
| 821 |
+
"োল": 818,
|
| 822 |
+
"োলা": 819,
|
| 823 |
+
"োড়": 820,
|
| 824 |
+
"ৌ": 821,
|
| 825 |
+
"্": 822,
|
| 826 |
+
"্চ": 823,
|
| 827 |
+
"্ট": 824,
|
| 828 |
+
"্ত": 825,
|
| 829 |
+
"্তি": 826,
|
| 830 |
+
"্তির": 827,
|
| 831 |
+
"্থ": 828,
|
| 832 |
+
"্ধ": 829,
|
| 833 |
+
"্ন": 830,
|
| 834 |
+
"্প": 831,
|
| 835 |
+
"্ব": 832,
|
| 836 |
+
"্বে": 833,
|
| 837 |
+
"্ভ": 834,
|
| 838 |
+
"্ম": 835,
|
| 839 |
+
"্মান": 836,
|
| 840 |
+
"্য": 837,
|
| 841 |
+
"্যন্ত": 838,
|
| 842 |
+
"্যপ্র": 839,
|
| 843 |
+
"্যা": 840,
|
| 844 |
+
"্যাত": 841,
|
| 845 |
+
"্যাল": 842,
|
| 846 |
+
"্যালয়ের": 843,
|
| 847 |
+
"্যে": 844,
|
| 848 |
+
"্যের": 845,
|
| 849 |
+
"্র": 846,
|
| 850 |
+
"্রহ": 847,
|
| 851 |
+
"্ল": 848,
|
| 852 |
+
"্ষ": 849,
|
| 853 |
+
"ৎ": 850,
|
| 854 |
+
"ৎস": 851,
|
| 855 |
+
"ৎসর্": 852,
|
| 856 |
+
"ৎসর্গ": 853,
|
| 857 |
+
"": 854,
|
| 858 |
+
"": 855,
|
| 859 |
+
"": 856,
|
| 860 |
+
"": 857,
|
| 861 |
+
"": 858,
|
| 862 |
+
"": 859,
|
| 863 |
+
"": 860,
|
| 864 |
+
"": 861,
|
| 865 |
+
"ৗ": 862,
|
| 866 |
+
"": 863,
|
| 867 |
+
"": 864,
|
| 868 |
+
"": 865,
|
| 869 |
+
"": 866,
|
| 870 |
+
"ড়": 867,
|
| 871 |
+
"ড়ি": 868,
|
| 872 |
+
"ড়িতে": 869,
|
| 873 |
+
"ড়িয়ে": 870,
|
| 874 |
+
"ঢ়": 871,
|
| 875 |
+
"": 872,
|
| 876 |
+
"য়": 873,
|
| 877 |
+
"য়ে": 874,
|
| 878 |
+
"য়েক": 875,
|
| 879 |
+
"য়ের": 876,
|
| 880 |
+
"ৠ": 877,
|
| 881 |
+
"ৡ": 878,
|
| 882 |
+
"ৢ": 879,
|
| 883 |
+
"ৣ": 880,
|
| 884 |
+
"": 881,
|
| 885 |
+
"": 882,
|
| 886 |
+
"০": 883,
|
| 887 |
+
"১": 884,
|
| 888 |
+
"২": 885,
|
| 889 |
+
"৩": 886,
|
| 890 |
+
"৪": 887,
|
| 891 |
+
"৫": 888,
|
| 892 |
+
"৬": 889,
|
| 893 |
+
"৭": 890,
|
| 894 |
+
"৮": 891,
|
| 895 |
+
"৯": 892,
|
| 896 |
+
"ৰ": 893,
|
| 897 |
+
"ৱ": 894,
|
| 898 |
+
"৲": 895,
|
| 899 |
+
"৳": 896,
|
| 900 |
+
"৴": 897,
|
| 901 |
+
"৵": 898,
|
| 902 |
+
"৶": 899,
|
| 903 |
+
"৷": 900,
|
| 904 |
+
"৸": 901,
|
| 905 |
+
"৹": 902,
|
| 906 |
+
"৺": 903,
|
| 907 |
+
"৻": 904,
|
| 908 |
+
"ৼ": 905,
|
| 909 |
+
"৽": 906,
|
| 910 |
+
"৾": 907,
|
| 911 |
+
"": 908
|
| 912 |
+
},
|
| 913 |
+
"merges": {
|
| 914 |
+
"া|র": "ার",
|
| 915 |
+
" |ত": " ত",
|
| 916 |
+
" |স": " স",
|
| 917 |
+
" |ক": " ক",
|
| 918 |
+
"ে|র": "ের",
|
| 919 |
+
"্|র": "্র",
|
| 920 |
+
" |প": " প",
|
| 921 |
+
" |আ": " আ",
|
| 922 |
+
" |ব": " ব",
|
| 923 |
+
"্|য": "্য",
|
| 924 |
+
" |ন": " ন",
|
| 925 |
+
" ত|া": " তা",
|
| 926 |
+
"ি|ল": "িল",
|
| 927 |
+
" |অ": " অ",
|
| 928 |
+
"্|ত": "্ত",
|
| 929 |
+
"ছ|িল": "ছিল",
|
| 930 |
+
" |দ": " দ",
|
| 931 |
+
"া|ন": "ান",
|
| 932 |
+
" |এ": " এ",
|
| 933 |
+
" তা|ঁ": " তাঁ",
|
| 934 |
+
"র|ে": "রে",
|
| 935 |
+
"য়|ে": "য়ে",
|
| 936 |
+
"ে|ন": "েন",
|
| 937 |
+
"ি|ক": "িক",
|
| 938 |
+
"র|্": "র্",
|
| 939 |
+
" তাঁ|র": " তাঁর",
|
| 940 |
+
"্|ষ": "্ষ",
|
| 941 |
+
" |ছিল": " ছিল",
|
| 942 |
+
" |ম": " ম",
|
| 943 |
+
"ি|ত": "িত",
|
| 944 |
+
"ি|ন": "িন",
|
| 945 |
+
" প|্র": " প্র",
|
| 946 |
+
" আ|ম": " আম",
|
| 947 |
+
" |য": " য",
|
| 948 |
+
"ক|ে": "কে",
|
| 949 |
+
" |শ": " শ",
|
| 950 |
+
"া|ত": "াত",
|
| 951 |
+
" ন|ি": " নি",
|
| 952 |
+
"া|য়": "ায়",
|
| 953 |
+
" |হ": " হ",
|
| 954 |
+
"্|ব": "্ব",
|
| 955 |
+
"দ|ের": "দের",
|
| 956 |
+
"ক|্ষ": "ক্ষ",
|
| 957 |
+
" |র": " র",
|
| 958 |
+
" |জ": " জ",
|
| 959 |
+
" ক|রে": " করে",
|
| 960 |
+
"ন|্": "ন্",
|
| 961 |
+
" |উ": " উ",
|
| 962 |
+
" |ছ": " ছ",
|
| 963 |
+
"্য|ে": "্যে",
|
| 964 |
+
"শ|্র": "শ্র",
|
| 965 |
+
" এ|ক": " এক",
|
| 966 |
+
" ক|র": " কর",
|
| 967 |
+
"ল|ে": "লে",
|
| 968 |
+
" ত|ার": " তার",
|
| 969 |
+
" ক|া": " কা",
|
| 970 |
+
" ন|া": " না",
|
| 971 |
+
" স|ম": " সম",
|
| 972 |
+
"শ্র|ম": "শ্রম",
|
| 973 |
+
" প|র": " পর",
|
| 974 |
+
"থ|া": "থা",
|
| 975 |
+
" |গ": " গ",
|
| 976 |
+
" ব|ি": " বি",
|
| 977 |
+
" |ভ": " ভ",
|
| 978 |
+
" আম|ার": " আমার",
|
| 979 |
+
"িন|ি": "িনি",
|
| 980 |
+
" স|া": " সা",
|
| 981 |
+
"ত|ে": "তে",
|
| 982 |
+
" |চ": " চ",
|
| 983 |
+
"াত|্র": "াত্র",
|
| 984 |
+
" ত|িনি": " তিনি",
|
| 985 |
+
"ষ|্": "ষ্",
|
| 986 |
+
" স|ে": " সে",
|
| 987 |
+
"ব|ে": "বে",
|
| 988 |
+
"স|্ত": "স্ত",
|
| 989 |
+
"ত|ি": "তি",
|
| 990 |
+
" এ|ই": " এই",
|
| 991 |
+
"ু|ম": "ুম",
|
| 992 |
+
"্|প": "্প",
|
| 993 |
+
" হ|য়ে": " হয়ে",
|
| 994 |
+
"ছ|ে": "ছে",
|
| 995 |
+
"া|ল": "াল",
|
| 996 |
+
"িক|্ষ": "িক্ষ",
|
| 997 |
+
"শ্রম|ের": "শ্রমের",
|
| 998 |
+
"্|ম": "্ম",
|
| 999 |
+
"ত|া": "তা",
|
| 1000 |
+
"ন|ে": "নে",
|
| 1001 |
+
"ন|া": "না",
|
| 1002 |
+
"ছিল|েন": "ছিলেন",
|
| 1003 |
+
"ষ্|ট": "ষ্ট",
|
| 1004 |
+
"খ|ন": "খন",
|
| 1005 |
+
"ব|া": "বা",
|
| 1006 |
+
"ভ|া": "ভা",
|
| 1007 |
+
" ছ|াত্র": " ছাত্র",
|
| 1008 |
+
" |ও": " ও",
|
| 1009 |
+
"থ|ে": "থে",
|
| 1010 |
+
"িক|ে": "িকে",
|
| 1011 |
+
"ৃ|ত": "ৃত",
|
| 1012 |
+
"ল|া": "লা",
|
| 1013 |
+
"ো|গ": "োগ",
|
| 1014 |
+
"্ত|ি": "্তি",
|
| 1015 |
+
"জ|ন": "জন",
|
| 1016 |
+
"ঙ|্": "ঙ্",
|
| 1017 |
+
"ঙ্|গ": "ঙ্গ",
|
| 1018 |
+
" স|ত": " সত",
|
| 1019 |
+
" শ|িক্ষ": " শিক্ষ",
|
| 1020 |
+
" নি|য়ে": " নিয়ে",
|
| 1021 |
+
" ব|া": " বা",
|
| 1022 |
+
"ট|া": "টা",
|
| 1023 |
+
"ল|্প": "ল্প",
|
| 1024 |
+
"্|চ": "্চ",
|
| 1025 |
+
" উ|প": " উপ",
|
| 1026 |
+
"ি|য়ে": "িয়ে",
|
| 1027 |
+
" য|ে": " যে",
|
| 1028 |
+
" আম|ি": " আমি",
|
| 1029 |
+
"ক|ার": "কার",
|
| 1030 |
+
"া|শ": "াশ",
|
| 1031 |
+
" |থে": " থে",
|
| 1032 |
+
" থে|কে": " থেকে",
|
| 1033 |
+
" আ|শ্রমের": " আশ্রমের",
|
| 1034 |
+
" ক|ো": " কো",
|
| 1035 |
+
"ট|ি": "টি",
|
| 1036 |
+
" ব|ে": " বে",
|
| 1037 |
+
"ব|ার": "বার",
|
| 1038 |
+
" ম|ধ": " মধ",
|
| 1039 |
+
" মধ|্যে": " মধ্যে",
|
| 1040 |
+
" আ|র": " আর",
|
| 1041 |
+
"্|ধ": "্ধ",
|
| 1042 |
+
"ন্|ধ": "ন্ধ",
|
| 1043 |
+
"ী|শ": "ীশ",
|
| 1044 |
+
"হ|িত": "হিত",
|
| 1045 |
+
" স|ং": " সং",
|
| 1046 |
+
"খ|ান": "খান",
|
| 1047 |
+
"ন|ের": "নের",
|
| 1048 |
+
" দ|ে": " দে",
|
| 1049 |
+
"ম|া": "মা",
|
| 1050 |
+
" অ|ন": " অন",
|
| 1051 |
+
"ব|ি": "বি",
|
| 1052 |
+
"ক্ষ|া": "ক্ষা",
|
| 1053 |
+
"া|স": "াস",
|
| 1054 |
+
"ঙ্গ|ে": "ঙ্গে",
|
| 1055 |
+
" সত|ীশ": " সতীশ",
|
| 1056 |
+
"ন্|দ": "ন্দ",
|
| 1057 |
+
" তাঁ|কে": " তাঁকে",
|
| 1058 |
+
"ূ|প": "ূপ",
|
| 1059 |
+
"ান|্ত": "ান্ত",
|
| 1060 |
+
" পর|ি": " পরি",
|
| 1061 |
+
"ম|ান": "মান",
|
| 1062 |
+
" দ|িকে": " দিকে",
|
| 1063 |
+
" প|া": " পা",
|
| 1064 |
+
" ত|খন": " তখন",
|
| 1065 |
+
" প|ড়": " পড়",
|
| 1066 |
+
" র|া": " রা",
|
| 1067 |
+
" অ|ল্প": " অল্প",
|
| 1068 |
+
" কা|জ": " কাজ",
|
| 1069 |
+
"ু|ন": "ুন",
|
| 1070 |
+
"ক্ষ|ে": "ক্ষে",
|
| 1071 |
+
" আ|ত": " আত",
|
| 1072 |
+
" আত|্ম": " আত্ম",
|
| 1073 |
+
"দ|িন": "দিন",
|
| 1074 |
+
" ছিল|েন": " ছিলেন",
|
| 1075 |
+
"প|ন": "পন",
|
| 1076 |
+
" প|ার": " পার",
|
| 1077 |
+
"ল|েন": "লেন",
|
| 1078 |
+
"িন|্ত": "িন্ত",
|
| 1079 |
+
" শিক্ষ|ক": " শিক্ষক",
|
| 1080 |
+
"দ|ান": "দান",
|
| 1081 |
+
" প্র|তি": " প্রতি",
|
| 1082 |
+
"্|থ": "্থ",
|
| 1083 |
+
" সা|হিত": " সাহিত",
|
| 1084 |
+
" দ|্ব": " দ্ব",
|
| 1085 |
+
"ন|্ত": "ন্ত",
|
| 1086 |
+
" জ|ন": " জন",
|
| 1087 |
+
"ল|ের": "লের",
|
| 1088 |
+
" এ|ব": " এব",
|
| 1089 |
+
" এব|ং": " এবং",
|
| 1090 |
+
"য়|ের": "য়ের",
|
| 1091 |
+
" গ|ে": " গে",
|
| 1092 |
+
" কর|তে": " করতে",
|
| 1093 |
+
"ী|র": "ীর",
|
| 1094 |
+
" অন|ু": " অনু",
|
| 1095 |
+
" তা|দের": " তাদের",
|
| 1096 |
+
" স|্ব": " স্ব",
|
| 1097 |
+
" |খ": " খ",
|
| 1098 |
+
" ক|ার": " কার",
|
| 1099 |
+
"্য|া": "্যা",
|
| 1100 |
+
"স|ে": "সে",
|
| 1101 |
+
" ক|িন্ত": " কিন্ত",
|
| 1102 |
+
" কিন্ত|ু": " কিন্তু",
|
| 1103 |
+
" স|ঙ্গে": " সঙ্গে",
|
| 1104 |
+
" র|ূপ": " রূপ",
|
| 1105 |
+
" এক|টা": " একটা",
|
| 1106 |
+
"ৃ|ষ্ট": "ৃষ্ট",
|
| 1107 |
+
"ী|র্": "ীর্",
|
| 1108 |
+
" দ্ব|ার": " দ্বার",
|
| 1109 |
+
"ি|ছ": "িছ",
|
| 1110 |
+
" প্র|া": " প্রা",
|
| 1111 |
+
"ী|ন": "ীন",
|
| 1112 |
+
" অ|তি": " অতি",
|
| 1113 |
+
"ক|া": "কা",
|
| 1114 |
+
"ু|র": "ুর",
|
| 1115 |
+
"িত|ে": "িতে",
|
| 1116 |
+
" দে|খ": " দেখ",
|
| 1117 |
+
" অ|ব": " অব",
|
| 1118 |
+
"দ|্ধ": "দ্ধ",
|
| 1119 |
+
" স|র্": " সর্",
|
| 1120 |
+
"র্|শ": "র্শ",
|
| 1121 |
+
" |থা": " থা",
|
| 1122 |
+
" কা|ছে": " কাছে",
|
| 1123 |
+
" য|া": " যা",
|
| 1124 |
+
" ক|থা": " কথা",
|
| 1125 |
+
" ভ|া": " ভা",
|
| 1126 |
+
"প|্র": "প্র",
|
| 1127 |
+
"ন|ো": "নো",
|
| 1128 |
+
" উ|চ": " উচ",
|
| 1129 |
+
" ম|ত": " মত",
|
| 1130 |
+
" হয়ে|ছিল": " হয়েছিল",
|
| 1131 |
+
" পর|ী": " পরী",
|
| 1132 |
+
"পন|ার": "পনার",
|
| 1133 |
+
" ব|ন্ধ": " বন্ধ",
|
| 1134 |
+
" আম|া": " আমা",
|
| 1135 |
+
" কাজ|ে": " কাজে",
|
| 1136 |
+
" য|দ": " যদ",
|
| 1137 |
+
" যদ|ি": " যদি",
|
| 1138 |
+
" য|োগ": " যোগ",
|
| 1139 |
+
"ক|্ত": "ক্ত",
|
| 1140 |
+
" ছাত্র|দের": " ছাত্রদের",
|
| 1141 |
+
"ার|্থ": "ার্থ",
|
| 1142 |
+
" ন|ত": " নত",
|
| 1143 |
+
" নত|ুন": " নতুন",
|
| 1144 |
+
"আ|শ্রমের": "আশ্রমের",
|
| 1145 |
+
" সাহিত|্য": " সাহিত্য",
|
| 1146 |
+
" কর|ত": " করত",
|
| 1147 |
+
" স|ৃষ্ট": " সৃষ্ট",
|
| 1148 |
+
"ি|র": "ির",
|
| 1149 |
+
" সে|খান": " সেখান",
|
| 1150 |
+
"ি|ম": "িম",
|
| 1151 |
+
" |ই": " ই",
|
| 1152 |
+
"চ|ীন": "চীন",
|
| 1153 |
+
" দ|ু": " দু",
|
| 1154 |
+
"ধ|ান": "ধান",
|
| 1155 |
+
" ন|ে": " নে",
|
| 1156 |
+
" প|রে": " পরে",
|
| 1157 |
+
"র|্ত": "র্ত",
|
| 1158 |
+
"র|া": "রা",
|
| 1159 |
+
" আ|শ্রম": " আশ্রম",
|
| 1160 |
+
"ূ|র্": "ূর্",
|
| 1161 |
+
"দ|ার": "দার",
|
| 1162 |
+
" ব|য়": " বয়",
|
| 1163 |
+
"দ|র্শ": "দর্শ",
|
| 1164 |
+
" ছ|ে": " ছে",
|
| 1165 |
+
"ছিল|ুম": "ছিলুম",
|
| 1166 |
+
"স|্ব": "স্ব",
|
| 1167 |
+
"র্|ম": "র্ম",
|
| 1168 |
+
" কো|নো": " কোনো",
|
| 1169 |
+
" চ|ে": " চে",
|
| 1170 |
+
"স|া": "সা",
|
| 1171 |
+
"ন্|ন": "ন্ন",
|
| 1172 |
+
" কার|ণ": " কারণ",
|
| 1173 |
+
" অ|ধ": " অধ",
|
| 1174 |
+
"ু|ণ": "ুণ",
|
| 1175 |
+
" ব|ল": " বল",
|
| 1176 |
+
" এ|সে": " এসে",
|
| 1177 |
+
" বন্ধ|ু": " বন্ধু",
|
| 1178 |
+
" দ|িয়ে": " দিয়ে",
|
| 1179 |
+
" বি|শ": " বিশ",
|
| 1180 |
+
"জ|্": "জ্",
|
| 1181 |
+
"ভা|বে": "ভাবে",
|
| 1182 |
+
"িক|ার": "িকার",
|
| 1183 |
+
" চ|ল": " চল",
|
| 1184 |
+
" প|ে": " পে",
|
| 1185 |
+
" সে|ই": " সেই",
|
| 1186 |
+
" সা|ধ": " সাধ",
|
| 1187 |
+
" করে|ছিলেন": " করেছিল��ন",
|
| 1188 |
+
"ভা|ব": "ভাব",
|
| 1189 |
+
" অ|ক": " অক",
|
| 1190 |
+
" উচ|্চ": " উচ্চ",
|
| 1191 |
+
" ব|িক": " বিক",
|
| 1192 |
+
" বিক|াশ": " বিকাশ",
|
| 1193 |
+
"া|ই": "াই",
|
| 1194 |
+
" সং|ক": " সংক",
|
| 1195 |
+
" স|ী": " সী",
|
| 1196 |
+
"গ|া": "গা",
|
| 1197 |
+
" ম|া": " মা",
|
| 1198 |
+
"ু|ব": "ুব",
|
| 1199 |
+
" জ|া": " জা",
|
| 1200 |
+
"ত|্ত": "ত্ত",
|
| 1201 |
+
" প্রা|চীন": " প্রাচীন",
|
| 1202 |
+
"ল|ায়": "লায়",
|
| 1203 |
+
" বে|দ": " বেদ",
|
| 1204 |
+
" সা|ম": " সাম",
|
| 1205 |
+
" পড়|ে": " পড়ে",
|
| 1206 |
+
"্|ন": "্ন",
|
| 1207 |
+
"ড়|ি": "ড়ি",
|
| 1208 |
+
"এ|ক": "এক",
|
| 1209 |
+
"্র|হ": "্রহ",
|
| 1210 |
+
" হয়ে|ছে": " হয়েছে",
|
| 1211 |
+
" |ল": " ল",
|
| 1212 |
+
"ক|াশ": "কাশ",
|
| 1213 |
+
"্|ভ": "্ভ",
|
| 1214 |
+
"ু|ল": "ুল",
|
| 1215 |
+
" র|ক্ষ": " রক্ষ",
|
| 1216 |
+
"স|ার": "সার",
|
| 1217 |
+
"াত|ে": "াতে",
|
| 1218 |
+
" |লা": " লা",
|
| 1219 |
+
" বয়|স": " বয়স",
|
| 1220 |
+
"্তি|র": "্তির",
|
| 1221 |
+
"ে|ষ": "েষ",
|
| 1222 |
+
" ছে|লে": " ছেলে",
|
| 1223 |
+
"ত|েন": "তেন",
|
| 1224 |
+
"দ|্র": "দ্র",
|
| 1225 |
+
"প|র": "পর",
|
| 1226 |
+
"ান|ের": "ানের",
|
| 1227 |
+
" স|হ": " সহ",
|
| 1228 |
+
"ত|ায়": "তায়",
|
| 1229 |
+
" বি|দ": " বিদ",
|
| 1230 |
+
" বে|ত": " বেত",
|
| 1231 |
+
" হ|ত": " হত",
|
| 1232 |
+
" সম|স্ত": " সমস্ত",
|
| 1233 |
+
"ু|গ": "ুগ",
|
| 1234 |
+
" দ|ান": " দান",
|
| 1235 |
+
" চে|ষ্ট": " চেষ্ট",
|
| 1236 |
+
" আ|র্": " আর্",
|
| 1237 |
+
" ন|য়": " নয়",
|
| 1238 |
+
" অ|জ": " অজ",
|
| 1239 |
+
" অজ|িত": " অজিত",
|
| 1240 |
+
" সতীশ|ের": " সতীশের",
|
| 1241 |
+
" ক|ে": " কে",
|
| 1242 |
+
" ম|ু": " মু",
|
| 1243 |
+
" |ধ": " ধ",
|
| 1244 |
+
" দ|িল": " দিল",
|
| 1245 |
+
" আ|পনার": " আপনার",
|
| 1246 |
+
"া|দ": "াদ",
|
| 1247 |
+
" তার|া": " তারা",
|
| 1248 |
+
" শ|্র": " শ্র",
|
| 1249 |
+
" শ্র|দ্ধ": " শ্রদ্ধ",
|
| 1250 |
+
"প|্ত": "প্ত",
|
| 1251 |
+
"ৃ|প": "ৃপ",
|
| 1252 |
+
"ণ|তা": "ণতা",
|
| 1253 |
+
"ু|ও": "ুও",
|
| 1254 |
+
" সর্|ব": " সর্ব",
|
| 1255 |
+
" ক|খন": " কখন",
|
| 1256 |
+
" কখন|ো": " কখনো",
|
| 1257 |
+
" পে|য়ে": " পেয়ে",
|
| 1258 |
+
" কা|লের": " কালের",
|
| 1259 |
+
" |২": " ২",
|
| 1260 |
+
" শ|ান্ত": " শান্ত",
|
| 1261 |
+
"ো|ট": "োট",
|
| 1262 |
+
"ক্ষ|ি": "ক্ষি",
|
| 1263 |
+
"ক্ষি|ণ": "ক্ষিণ",
|
| 1264 |
+
" দ|ীর্": " দীর্",
|
| 1265 |
+
" দীর্|ঘ": " দীর্ঘ",
|
| 1266 |
+
"শ|্চ": "শ্চ",
|
| 1267 |
+
" কো|থা": " কোথা",
|
| 1268 |
+
" কোথা|ও": " কোথাও",
|
| 1269 |
+
" তা|ল": " তাল",
|
| 1270 |
+
"য়ে|ক": "য়েক",
|
| 1271 |
+
" উ|ত্ত": " উত্ত",
|
| 1272 |
+
" উত্ত|র": " উত্তর",
|
| 1273 |
+
" বা|ঁ": " বাঁ",
|
| 1274 |
+
" এক|টি": " একটি",
|
| 1275 |
+
" সাম|নে": " সামনে",
|
| 1276 |
+
" গ|া": " গা",
|
| 1277 |
+
"ছ|ের": "ছের",
|
| 1278 |
+
"্য|ন্ত": "্যন্ত",
|
| 1279 |
+
" তখন|ো": " তখনো",
|
| 1280 |
+
"ী|ব": "ীব",
|
| 1281 |
+
" জন|্যে": " জন্যে",
|
| 1282 |
+
"ত|লা": "তলা",
|
| 1283 |
+
" বা|ড়ি": " বাড়ি",
|
| 1284 |
+
"ক|িছ": "কিছ",
|
| 1285 |
+
"কিছ|ু": "কিছু",
|
| 1286 |
+
" উপ|রে": " উপরে",
|
| 1287 |
+
"র্ত|মান": "র্তমান",
|
| 1288 |
+
" বি|স্ত": " বিস্ত",
|
| 1289 |
+
" ব|হ": " বহ",
|
| 1290 |
+
"ক|াল": "কাল",
|
| 1291 |
+
" দেখ|া": " দেখা",
|
| 1292 |
+
" প|ূর্": " পূর্",
|
| 1293 |
+
" জ|ম": " জম",
|
| 1294 |
+
" সেখান|ে": " সেখানে",
|
| 1295 |
+
" আ|হ": " আহ",
|
| 1296 |
+
"ম|্ভ": "ম্ভ",
|
| 1297 |
+
"ার|ি": "ারি",
|
| 1298 |
+
" প্র|থ": " প্রথ",
|
| 1299 |
+
" প্রথ|ম": " প্রথম",
|
| 1300 |
+
"ল|ার": "লার",
|
| 1301 |
+
" |ঘ": " ঘ",
|
| 1302 |
+
" উপ|া": " উপা",
|
| 1303 |
+
"ধ|্য": "ধ্য",
|
| 1304 |
+
"্য|াল": "্যাল",
|
| 1305 |
+
"্যাল|য়ের": "্যালয়ের",
|
| 1306 |
+
" বেত|ন": " বেতন",
|
| 1307 |
+
"ও|য়": "ওয়",
|
| 1308 |
+
" প্র|য়": " প্রয়",
|
| 1309 |
+
" প্রয়|ো": " প্রয়ো",
|
| 1310 |
+
" প্রয়ো|জন": " প্রয়োজন",
|
| 1311 |
+
" উপ|ল": " উপল",
|
| 1312 |
+
" উপল|ক্ষে": " উপলক্ষে",
|
| 1313 |
+
" অ|র্": " অর্",
|
| 1314 |
+
" সম|া": " সমা",
|
| 1315 |
+
"জ|ের": "জের",
|
| 1316 |
+
" রক্ষ|ার": " রক্ষার",
|
| 1317 |
+
" ব|্য": " ব্য",
|
| 1318 |
+
"ক|্তি": "ক্তি",
|
| 1319 |
+
"গ|ত": "গত",
|
| 1320 |
+
"ন্ত|্র": "ন্ত্র",
|
| 1321 |
+
"ম|াত্র": "মাত্র",
|
| 1322 |
+
" নি|র্": " নির্",
|
| 1323 |
+
"ষ|্য": "ষ্য",
|
| 1324 |
+
" আর্|থ": " আর্থ",
|
| 1325 |
+
" আর্থ|িক": " আর্থিক",
|
| 1326 |
+
" প্র|চ": " প্রচ",
|
| 1327 |
+
" র|ক্ষা": " রক্ষা",
|
| 1328 |
+
" কর|বার": " করবার",
|
| 1329 |
+
" ক|র্ম": " কর্ম",
|
| 1330 |
+
" অ|নে": " অনে",
|
| 1331 |
+
" অনে|ক": " অনেক",
|
| 1332 |
+
"খ|ে": "খে",
|
| 1333 |
+
" দ্বার|া": " দ্বারা",
|
| 1334 |
+
" পরী|ক্ষ": " পরীক্ষ",
|
| 1335 |
+
"য|োগ": "যোগ",
|
| 1336 |
+
"্|ট": "্ট",
|
| 1337 |
+
" অধ|্যা": " অধ্যা",
|
| 1338 |
+
" ম|নে": " মনে",
|
| 1339 |
+
"ো|ড়": "োড়",
|
| 1340 |
+
" সম|য়ে": " সময়ে",
|
| 1341 |
+
" ব|াল": " বাল",
|
| 1342 |
+
" বাল|ক": " বালক",
|
| 1343 |
+
" হ|য়": " হয়",
|
| 1344 |
+
" আমা|দের": " আমাদের",
|
| 1345 |
+
"ন|ি": "নি",
|
| 1346 |
+
" আ|স": " আস",
|
| 1347 |
+
" আমা|কে": " আমাকে",
|
| 1348 |
+
" দিয়ে|ছিলেন": " দিয়েছিলেন",
|
| 1349 |
+
" স|ব": " সব",
|
| 1350 |
+
"ণ|ে": "ণে",
|
| 1351 |
+
" প্র|ব": " প্রব",
|
| 1352 |
+
"ি|ষ্ট": "িষ্ট",
|
| 1353 |
+
" তা|তে": " তাতে",
|
| 1354 |
+
"ী|কার": "ীকার",
|
| 1355 |
+
" বল|লেন": " বললেন",
|
| 1356 |
+
" দ|িতে": " দিতে",
|
| 1357 |
+
"ল|ুম": "লুম",
|
| 1358 |
+
" পরী|ক্ষা": " পরীক্ষা",
|
| 1359 |
+
" পা|ঠ": " পাঠ",
|
| 1360 |
+
" দ|িত": " দিত",
|
| 1361 |
+
"ীর্|ণ": "ীর্ণ",
|
| 1362 |
+
"ঞ|্চ": "ঞ্চ",
|
| 1363 |
+
"ণ|্": "ণ্",
|
| 1364 |
+
"ণ্|ড": "ণ্ড",
|
| 1365 |
+
" ই|ং": " ইং",
|
| 1366 |
+
" ইং|রে": " ইংরে",
|
| 1367 |
+
" ইংরে|জ": " ইংরেজ",
|
| 1368 |
+
" ইংরেজ|ি": " ইংরেজি",
|
| 1369 |
+
"ভ|ীর": "ভীর",
|
| 1370 |
+
" ভা|ষ": " ভাষ",
|
| 1371 |
+
"জ্|ঞ": "জ্ঞ",
|
| 1372 |
+
"ন|কে": "নকে",
|
| 1373 |
+
" অ|ত": " অত",
|
| 1374 |
+
" শ|াস": " শাস",
|
| 1375 |
+
"ৎ|স": "ৎস",
|
| 1376 |
+
" বেদ|না": " বেদনা",
|
| 1377 |
+
" সম|্প": " সম্প",
|
| 1378 |
+
"ত|ার": "তার",
|
| 1379 |
+
" পরি|চ": " পরিচ",
|
| 1380 |
+
" পরিচ|য়": " পরিচয়",
|
| 1381 |
+
" সাধ|না": " সাধনা",
|
| 1382 |
+
"ত|্র": "ত্র",
|
| 1383 |
+
"ত্র|ে": "ত্রে",
|
| 1384 |
+
"ঞ|্": "ঞ্",
|
| 1385 |
+
"ঞ্|জ": "ঞ্জ",
|
| 1386 |
+
" জন|্য": " জন্য",
|
| 1387 |
+
"ু|ক্ত": "ুক্ত",
|
| 1388 |
+
"ৃপ|ণতা": "ৃপণতা",
|
| 1389 |
+
" রা|খ": " রাখ",
|
| 1390 |
+
" যদি|ও": " যদিও",
|
| 1391 |
+
"মা|ণ": "মাণ",
|
| 1392 |
+
" ত|ব": " তব",
|
| 1393 |
+
" তব|ুও": " তবুও",
|
| 1394 |
+
" আ|ন": " আন",
|
| 1395 |
+
"ন্|দের": "ন্দের",
|
| 1396 |
+
" স্ব|ভাব": " স্বভাব",
|
| 1397 |
+
" অক|ৃত": " অকৃত",
|
| 1398 |
+
" আত্ম|দান": " আত্মদান",
|
| 1399 |
+
" য|থ": " যথ",
|
| 1400 |
+
" যথ|ার্থ": " যথার্থ",
|
| 1401 |
+
" শিক্ষক|ের": " শিক্ষকের",
|
| 1402 |
+
" আ|দর্শ": " আদর্শ",
|
| 1403 |
+
"না|কে": "নাকে",
|
| 1404 |
+
" ভ|িত": " ভিত",
|
| 1405 |
+
" শ্রদ্ধ|ার": " শ্রদ্ধার",
|
| 1406 |
+
"ছ|েন": "ছেন",
|
| 1407 |
+
"হ|ে": "হে",
|
| 1408 |
+
" প|দ": " পদ",
|
| 1409 |
+
"চ|া": "চা",
|
| 1410 |
+
" করত|ুম": " করতুম",
|
| 1411 |
+
" সৃষ্ট|ির": " সৃষ্টির",
|
| 1412 |
+
" সংক|ল্প": " সংকল্প",
|
| 1413 |
+
"লে|ম": "লেম",
|
| 1414 |
+
" শান্ত|িন": " শান্তিন",
|
| 1415 |
+
" শান্তিন|িকে": " শান্তিনিকে",
|
| 1416 |
+
" শান্তিনিকে|ত": " শান্তিনিকেত",
|
| 1417 |
+
" শান্তিনিকেত|নের": " শান্তিনিকেতনের",
|
| 1418 |
+
" প্র|ান্ত": " প্রান্ত",
|
| 1419 |
+
" পরি|ধ": " পরিধ",
|
| 1420 |
+
" ছ|োট": " ছোট",
|
| 1421 |
+
" ছোট|ো": " ছোটো",
|
| 1422 |
+
" দ|ক্ষিণ": " দক্ষিণ",
|
| 1423 |
+
" সী|মান": " সীমান",
|
| 1424 |
+
" সীমান|ায়": " সীমানায়",
|
| 1425 |
+
"বা|ঁ": "বাঁ",
|
| 1426 |
+
" শ|াল": " শাল",
|
| 1427 |
+
"ব|িত": "বিত",
|
| 1428 |
+
"বে|শ": "বেশ",
|
| 1429 |
+
" প|িছ": " পিছ",
|
| 1430 |
+
"বা|গ": "বাগ",
|
| 1431 |
+
"শ্চ|িম": "শ্চিম",
|
| 1432 |
+
" জা|ম": " জাম",
|
| 1433 |
+
" দু|টি": " দুটি",
|
| 1434 |
+
" ত|লায়": " তলায়",
|
| 1435 |
+
"্ব|ে": "্বে",
|
| 1436 |
+
" বাঁ|ধান": " বাঁধান",
|
| 1437 |
+
" বাঁধান|ো": " বাঁধানো",
|
| 1438 |
+
" নি|র": " নির",
|
| 1439 |
+
" গা|ছের": " গাছের",
|
| 1440 |
+
" নে|ই": " নেই",
|
| 1441 |
+
"ি|গ": "িগ",
|
| 1442 |
+
" পর|্যন্ত": " পর্যন্ত",
|
| 1443 |
+
" মা|ঠ": " মাঠ",
|
| 1444 |
+
" অতি|থ": " অতিথ",
|
| 1445 |
+
" অতিথ|ি": " অতিথি",
|
| 1446 |
+
" দ|ো": " দো",
|
| 1447 |
+
"ঠ|া": "ঠা",
|
| 1448 |
+
" তার|ই": " তারই",
|
| 1449 |
+
" ক|দ": " কদ",
|
| 1450 |
+
" ছ|ায়": " ছায়",
|
| 1451 |
+
" পা|কা": " পাকা",
|
| 1452 |
+
" প|ুর": " পুর",
|
| 1453 |
+
"ো|ধ": "োধ",
|
| 1454 |
+
" সং|গ": " সংগ",
|
| 1455 |
+
"ড়|িয়ে": "ড়িয়ে",
|
| 1456 |
+
" ব|র্তমান": " বর্তমান",
|
| 1457 |
+
" স|্": " স্",
|
| 1458 |
+
"ড়|িতে": "ড়ি��ে",
|
| 1459 |
+
" বহ|ু": " বহু",
|
| 1460 |
+
"কাল|ের": "কালের",
|
| 1461 |
+
"শ্র|ে": "শ্রে",
|
| 1462 |
+
"শ্রে|ণ": "শ্রেণ",
|
| 1463 |
+
"ো|ল": "োল",
|
| 1464 |
+
"ন|্য": "ন্য",
|
| 1465 |
+
" রা|স্ত": " রাস্ত",
|
| 1466 |
+
" গে|ছে": " গেছে",
|
| 1467 |
+
" ল|ো": " লো",
|
| 1468 |
+
" লো|ক": " লোক",
|
| 1469 |
+
"মান|্য": "মান্য",
|
| 1470 |
+
" আহ|ার": " আহার",
|
| 1471 |
+
" র|োগ": " রোগ",
|
| 1472 |
+
" বিস্ত|ার": " বিস্তার",
|
| 1473 |
+
" আর|ম্ভ": " আরম্ভ",
|
| 1474 |
+
"রা|জ": "রাজ",
|
| 1475 |
+
" অব|কাশ": " অবকাশ",
|
| 1476 |
+
" ব|ৃ": " বৃ",
|
| 1477 |
+
" হ|াতে": " হাতে",
|
| 1478 |
+
"ম|্ব": "ম্ব",
|
| 1479 |
+
" বয়স|ের": " বয়সের",
|
| 1480 |
+
"স|্য": "স্য",
|
| 1481 |
+
"ৃত|্তির": "ৃত্তির",
|
| 1482 |
+
" শ|েষ": " শেষ",
|
| 1483 |
+
" নি|দর্শ": " নিদর্শ",
|
| 1484 |
+
" নিদর্শ|ন": " নিদর্শন",
|
| 1485 |
+
"াল|ী": "ালী",
|
| 1486 |
+
"ভ|ব": "ভব",
|
| 1487 |
+
" এক|ত": " একত",
|
| 1488 |
+
" থা|ক": " থাক",
|
| 1489 |
+
"েন|্": "েন্",
|
| 1490 |
+
"েন্|দ্র": "েন্দ্র",
|
| 1491 |
+
"েন্দ্র|না": "েন্দ্রনা",
|
| 1492 |
+
"েন্দ্রনা|থ": "েন্দ্রনাথ",
|
| 1493 |
+
" ক|য়েক": " কয়েক",
|
| 1494 |
+
"চ|র": "চর",
|
| 1495 |
+
" ঘ|রে": " ঘরে",
|
| 1496 |
+
"এ|ই": "এই",
|
| 1497 |
+
" ব|্রহ": " ব্রহ",
|
| 1498 |
+
" ব্রহ|্ম": " ব্রহ্ম",
|
| 1499 |
+
" ব্রহ্ম|ব": " ব্রহ্মব",
|
| 1500 |
+
" ব্রহ্মব|ান": " ব্রহ্মবান",
|
| 1501 |
+
" ব্রহ্মবান|্ধ": " ব্রহ্মবান্ধ",
|
| 1502 |
+
" ব্রহ্মবান্ধ|ব": " ব্রহ্মবান্ধব",
|
| 1503 |
+
" পড়|া": " পড়া",
|
| 1504 |
+
" পড়া|বার": " পড়াবার",
|
| 1505 |
+
" জ|ুগ": " জুগ",
|
| 1506 |
+
" জুগ|িয়ে": " জুগিয়ে",
|
| 1507 |
+
"ছ|ি": "ছি",
|
| 1508 |
+
"ু|লে": "ুলে",
|
| 1509 |
+
"কা|লে": "কালে",
|
| 1510 |
+
" রা|জ": " রাজ",
|
| 1511 |
+
"ষ্|ঠ": "ষ্ঠ",
|
| 1512 |
+
"গ|ের": "গের",
|
| 1513 |
+
"প|া": "পা",
|
| 1514 |
+
" ক|্র": " ক্র",
|
| 1515 |
+
"ি|য়": "িয়",
|
| 1516 |
+
"া|ক": "াক",
|
| 1517 |
+
" ন|িত": " নিত",
|
| 1518 |
+
"্য|প্র": "্যপ্র",
|
| 1519 |
+
" অ|ঙ্গ": " অঙ্গ",
|
| 1520 |
+
" ক|্ষ": " ক্ষ",
|
| 1521 |
+
"শ|ি": "শি",
|
| 1522 |
+
" সম|্ব": " সম্ব",
|
| 1523 |
+
" সম্ব|ন্ধ": " সম্বন্ধ",
|
| 1524 |
+
" থা|কা": " থাকা",
|
| 1525 |
+
" সত|্য": " সত্য",
|
| 1526 |
+
" সহ|জ": " সহজ",
|
| 1527 |
+
" উপা|য়ে": " উপায়ে",
|
| 1528 |
+
"জ|ে": "জে",
|
| 1529 |
+
" চেষ্ট|া": " চেষ্টা",
|
| 1530 |
+
" অ|সা": " অসা",
|
| 1531 |
+
"স|্ট": "স্ট",
|
| 1532 |
+
" অধ্যা|পনার": " অধ্যাপনার",
|
| 1533 |
+
" তাঁ|দের": " তাঁদের",
|
| 1534 |
+
" প্র|স": " প্রস",
|
| 1535 |
+
"জন|ের": "জনের",
|
| 1536 |
+
" ভ|ুল": " ভুল",
|
| 1537 |
+
" ভুল|তে": " ভুলতে",
|
| 1538 |
+
" অজিত|ক": " অজিতক",
|
| 1539 |
+
" অজিতক|ুম": " অজিতকুম",
|
| 1540 |
+
" অজিতকুম|ার": " অজিতকুমার",
|
| 1541 |
+
"চ|ন্দ": "চন্দ",
|
| 1542 |
+
"চন্দ|্র": "চন্দ্র",
|
| 1543 |
+
"পর|ী": "পরী",
|
| 1544 |
+
" প|াত": " পাত",
|
| 1545 |
+
" পাত|ায়": " পাতায়",
|
| 1546 |
+
" জ|ান": " জান",
|
| 1547 |
+
" এ|ম": " এম",
|
| 1548 |
+
" এম|ন": " এমন",
|
| 1549 |
+
" |লে": " লে",
|
| 1550 |
+
"খ|া": "খা",
|
| 1551 |
+
"জ্|জ": "জ্জ",
|
| 1552 |
+
"জ্জ|্ব": "জ্জ্ব",
|
| 1553 |
+
"জ্জ্ব|ল": "জ্জ্বল",
|
| 1554 |
+
"ম|তা": "মতা",
|
| 1555 |
+
"থ|ায়": "থায়",
|
| 1556 |
+
" বিদ|ায়": " বিদায়",
|
| 1557 |
+
" কর|া": " করা",
|
| 1558 |
+
" অ|স": " অস",
|
| 1559 |
+
"্ম|ান": "্মান",
|
| 1560 |
+
" স্ব|ীকার": " স্বীকার",
|
| 1561 |
+
" নিয়ে|ছিলেন": " নিয়েছিলেন",
|
| 1562 |
+
"ম|ার": "মার",
|
| 1563 |
+
" ম|নের": " মনের",
|
| 1564 |
+
" মু|খ": " মুখ",
|
| 1565 |
+
"ঁ|দের": "ঁদের",
|
| 1566 |
+
"ত|ুম": "তুম",
|
| 1567 |
+
" বিশ|্ব": " বিশ্ব",
|
| 1568 |
+
" বিশ্ব|বি": " বিশ্ববি",
|
| 1569 |
+
" বিশ্ববি|দ": " বিশ্ববিদ",
|
| 1570 |
+
" বিশ্ববিদ|্যালয়ের": " বিশ্ববিদ্যালয়ের",
|
| 1571 |
+
"র|ের": "রের",
|
| 1572 |
+
" ব|ড়": " বড়",
|
| 1573 |
+
" বড়|ো": " বড়ো",
|
| 1574 |
+
" জ|ীব": " জীব",
|
| 1575 |
+
"ই|ন": "ইন",
|
| 1576 |
+
" দ|ারি": " দারি",
|
| 1577 |
+
" দারি|দ্র": " দারিদ্র",
|
| 1578 |
+
"্য|ের": "্যের",
|
| 1579 |
+
" ভ|ার": " ভার",
|
| 1580 |
+
" দিল|েন": " দিলেন",
|
| 1581 |
+
" অ|গ": " অগ",
|
| 1582 |
+
"ো|চ": "োচ",
|
| 1583 |
+
" ম|াস": " মাস",
|
| 1584 |
+
" স|ঞ্চ": " সঞ্চ",
|
| 1585 |
+
"র|ণ": "রণ",
|
| 1586 |
+
" প্র|ত": " প্রত",
|
| 1587 |
+
" র|স": " রস",
|
| 1588 |
+
"ণ্ড|ার": "ণ্ডার",
|
| 1589 |
+
"ো|লা": "োলা",
|
| 1590 |
+
"খান|ে": "খানে",
|
| 1591 |
+
" চল|তে": " চলতে",
|
| 1592 |
+
" আ|স্ব": " আস্ব",
|
| 1593 |
+
" আস্ব|াদ": " আস্বাদ",
|
| 1594 |
+
" সাহিত|্যে": " সাহিত্যে",
|
| 1595 |
+
" স|ুগ": " সুগ",
|
| 1596 |
+
" সুগ|ভীর": " সুগভীর",
|
| 1597 |
+
" অ|ভ": " অভ",
|
| 1598 |
+
" মত|ো": " মতো",
|
| 1599 |
+
" ছাত্র|কে": " ছাত্রকে",
|
| 1600 |
+
" সংক|ীর্ণ": " সংকীর্ণ",
|
| 1601 |
+
"প|ুণ": "পুণ",
|
| 1602 |
+
" সাহিত্য|ের": " সাহিত্যের",
|
| 1603 |
+
" সাধ|ক": " সাধক",
|
| 1604 |
+
" দিত|েন": " দিতেন",
|
| 1605 |
+
" ছেলে|দের": " ছেলেদের",
|
| 1606 |
+
"ক|ের": "কের",
|
| 1607 |
+
" শাস|ন": " শাসন",
|
| 1608 |
+
" থা|কে": " থাকে",
|
| 1609 |
+
" পার|তেন": " পারতেন",
|
| 1610 |
+
" ম|ৃত": " মৃত",
|
| 1611 |
+
" মৃত|্য": " মৃত্য",
|
| 1612 |
+
" মৃত্য|ু": " মৃত্যু",
|
| 1613 |
+
" য|ার": " যার",
|
| 1614 |
+
" যার|া": " যারা",
|
| 1615 |
+
" হ|বে": " হবে",
|
| 1616 |
+
" সম্প|ূর্": " সম্পূর্",
|
| 1617 |
+
" এসে|ছিলেন": " এসেছিলেন",
|
| 1618 |
+
" জ|গ": " জগ",
|
| 1619 |
+
" জগ|দান": " জগদান",
|
| 1620 |
+
" জগদান|ন্দ": " জগদানন্দ",
|
| 1621 |
+
" প্র|ের": " প্রের",
|
| 1622 |
+
" ব|ৈ": " বৈ",
|
| 1623 |
+
" প্রব|ন্ধ": " প্রবন্ধ",
|
| 1624 |
+
"ক|ল": "কল",
|
| 1625 |
+
"ঞ্জ|ল": "ঞ্জল",
|
| 1626 |
+
" দেখ|ে": " দেখে",
|
| 1627 |
+
" অ|ভাব": " অভাব",
|
| 1628 |
+
" জম|ি": " জমি",
|
| 1629 |
+
" জমি|দার": " জমিদার",
|
| 1630 |
+
"য|ুক্ত": "যুক্ত",
|
| 1631 |
+
" ক|ৃপণতা": " কৃপণতা",
|
| 1632 |
+
" রাখ|তে": " রাখতে",
|
| 1633 |
+
" পরি|মাণ": " পরিমাণ",
|
| 1634 |
+
" আন|ন্দের": " আনন্দের",
|
| 1635 |
+
" প|ক্ষে": " পক্ষে",
|
| 1636 |
+
" শিক্ষ|া": " শিক্ষা",
|
| 1637 |
+
" স্বভাব|ের": " স্বভাবের",
|
| 1638 |
+
" অকৃত|্র": " অকৃত্র",
|
| 1639 |
+
" অকৃত্র|িম": " অকৃত্রিম",
|
| 1640 |
+
" সর্ব|ত": " সর্বত",
|
| 1641 |
+
" সর্বত|ো": " সর্বতো",
|
| 1642 |
+
" সর্বতো|ভাবে": " সর্বতোভাবে",
|
| 1643 |
+
" বালক|দের": " বালকদের",
|
| 1644 |
+
" এক|জন": " একজন",
|
| 1645 |
+
" বি|ষ": " বিষ",
|
| 1646 |
+
"ণ|্য": "ণ্য",
|
| 1647 |
+
" কা|ছ": " কাছ",
|
| 1648 |
+
" অধ|িকার": " অধিকার",
|
| 1649 |
+
" ব|স্ত": " বস্ত",
|
| 1650 |
+
" বস্ত|ু": " বস্তু",
|
| 1651 |
+
" বস্তু|ত": " বস্তুত",
|
| 1652 |
+
"শ|িক্ষ": "শিক্ষ",
|
| 1653 |
+
" শিক্ষ|ার": " শিক্ষার",
|
| 1654 |
+
"্|ল": "্ল",
|
| 1655 |
+
"র্|জন": "র্জন",
|
| 1656 |
+
" ভিত|রে": " ভিতরে",
|
| 1657 |
+
" সৃষ্ট|িকার": " সৃষ্টিকার",
|
| 1658 |
+
" সৃষ্টিকার|্যে": " সৃষ্টিকার্যে",
|
| 1659 |
+
" আ|প": " আপ",
|
| 1660 |
+
" আপ|নাকে": " আপনাকে",
|
| 1661 |
+
"ৎস|র্": "ৎসর্",
|
| 1662 |
+
"ৎসর্|গ": "ৎসর্গ",
|
| 1663 |
+
" স|্থ": " স্থ",
|
| 1664 |
+
" জ|্": " জ্",
|
| 1665 |
+
" জ্|ঞ": " জ্ঞ",
|
| 1666 |
+
" জ্ঞ|ানের": " জ্ঞানের",
|
| 1667 |
+
" ছাত্র|ের": " ছাত্রের",
|
| 1668 |
+
" শিক্ষক|তা": " শিক্ষকতা",
|
| 1669 |
+
" যোগ|্য": " যোগ্য",
|
| 1670 |
+
"কার|্যে": "কার্যে",
|
| 1671 |
+
"্য|াত": "্যাত",
|
| 1672 |
+
" পেয়ে|ছিলেন": " পেয়েছিলেন",
|
| 1673 |
+
"দিন|ের": "দিনের",
|
| 1674 |
+
" আদর্শ|ের": " আদর্শের",
|
| 1675 |
+
" ত|বে": " তবে",
|
| 1676 |
+
" গে|লেন": " গেলেন",
|
| 1677 |
+
"র|ূপ": "রূপ",
|
| 1678 |
+
"রূপ|ে": "রূপে",
|
| 1679 |
+
" কে|ব": " কেব",
|
| 1680 |
+
" কেব|ল": " কেবল",
|
| 1681 |
+
" সাধনা|ক্ষে": " সাধনাক্ষে",
|
| 1682 |
+
" সাধনাক্ষে|ত্রে": " সাধনাক্ষেত্রে",
|
| 1683 |
+
" ন|ান": " নান",
|
| 1684 |
+
" নান|া": " নানা",
|
| 1685 |
+
" আ|পন": " আপন",
|
| 1686 |
+
"চ|িত": "চিত",
|
| 1687 |
+
"চিত|্র": "চিত্র"
|
| 1688 |
+
},
|
| 1689 |
+
"vocab_size": 5000,
|
| 1690 |
+
"special_tokens": {
|
| 1691 |
+
"<PAD>": 0,
|
| 1692 |
+
"<UNK>": 1,
|
| 1693 |
+
"<BOS>": 2,
|
| 1694 |
+
"<EOS>": 3
|
| 1695 |
+
}
|
| 1696 |
+
}
|
bengali_bpe_tokenizer.py
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import re
|
| 2 |
+
import json
|
| 3 |
+
from collections import defaultdict, Counter
|
| 4 |
+
from typing import List, Dict, Tuple, Set
|
| 5 |
+
|
| 6 |
+
class BengaliBPETokenizer:
|
| 7 |
+
def __init__(self, vocab_size: int = 5000):
|
| 8 |
+
self.vocab_size = vocab_size
|
| 9 |
+
self.vocab = {}
|
| 10 |
+
self.merges = {}
|
| 11 |
+
self.special_tokens = {
|
| 12 |
+
'<PAD>': 0,
|
| 13 |
+
'<UNK>': 1,
|
| 14 |
+
'<BOS>': 2,
|
| 15 |
+
'<EOS>': 3
|
| 16 |
+
}
|
| 17 |
+
|
| 18 |
+
# Initialize basic Bengali character vocabulary
|
| 19 |
+
self.base_vocab = set()
|
| 20 |
+
self.bengali_letter_start_unicode = 0x0980
|
| 21 |
+
self.bengali_letter_end_unicode = 0x09FF
|
| 22 |
+
self._initialize_base_vocab()
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
def _initialize_base_vocab(self):
|
| 26 |
+
"""Initialize vocabulary with basic Bengali characters"""
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
for i in range(self.bengali_letter_start_unicode, self.bengali_letter_end_unicode + 1):
|
| 30 |
+
self.base_vocab.add(chr(i))
|
| 31 |
+
|
| 32 |
+
self.base_vocab.update([
|
| 33 |
+
' ', '\n', '\t' # Whitespace characters
|
| 34 |
+
])
|
| 35 |
+
|
| 36 |
+
def _get_stats(self, words: List[List[str]]) -> Dict[Tuple[str, str], int]:
|
| 37 |
+
"""Count frequency of adjacent pairs in the vocabulary"""
|
| 38 |
+
pairs = defaultdict(int)
|
| 39 |
+
for word in words:
|
| 40 |
+
for i in range(len(word) - 1):
|
| 41 |
+
pairs[tuple(word[i:i + 2])] += 1
|
| 42 |
+
return pairs
|
| 43 |
+
|
| 44 |
+
def _merge_vocab(self, words: List[List[str]], pair: Tuple[str, str]) -> List[List[str]]:
|
| 45 |
+
"""Merge all occurrences of the most frequent pair"""
|
| 46 |
+
first, second = pair
|
| 47 |
+
new_words = []
|
| 48 |
+
|
| 49 |
+
for word in words:
|
| 50 |
+
i = 0
|
| 51 |
+
new_word = []
|
| 52 |
+
while i < len(word):
|
| 53 |
+
if i < len(word) - 1 and word[i] == first and word[i + 1] == second:
|
| 54 |
+
new_word.append(first + second)
|
| 55 |
+
i += 2
|
| 56 |
+
else:
|
| 57 |
+
new_word.append(word[i])
|
| 58 |
+
i += 1
|
| 59 |
+
new_words.append(new_word)
|
| 60 |
+
|
| 61 |
+
return new_words
|
| 62 |
+
|
| 63 |
+
def train(self, texts: List[str], min_freq: int = 2) -> None:
|
| 64 |
+
"""Train BPE model on texts"""
|
| 65 |
+
|
| 66 |
+
# Regular expression for extracting Bengali words
|
| 67 |
+
bengali_word_pattern = re.compile(r""" ?[\u0980-\u09FF]+| ?[^\s]+|\s+(?!\S)|\s+""")
|
| 68 |
+
|
| 69 |
+
# Split texts into characters
|
| 70 |
+
words = []
|
| 71 |
+
for text in texts:
|
| 72 |
+
# Extract words based on the Bengali pattern
|
| 73 |
+
extracted_words = bengali_word_pattern.findall(text)
|
| 74 |
+
#print("extracted words:", extracted_words)
|
| 75 |
+
for word in extracted_words:
|
| 76 |
+
chars = list(word)
|
| 77 |
+
# Filter valid Bengali characters
|
| 78 |
+
valid_chars = [c for c in chars if c in self.base_vocab or c.isspace()]
|
| 79 |
+
if valid_chars:
|
| 80 |
+
words.append(valid_chars)
|
| 81 |
+
|
| 82 |
+
#print("words:", words)
|
| 83 |
+
|
| 84 |
+
vocab = self.base_vocab.copy()
|
| 85 |
+
num_merges = self.vocab_size - len(self.special_tokens) - len(vocab)
|
| 86 |
+
print("Maximum num_merges : ", num_merges)
|
| 87 |
+
# Perform BPE merges
|
| 88 |
+
for i in range(num_merges):
|
| 89 |
+
pairs = self._get_stats(words)
|
| 90 |
+
if i % 100 == 0:
|
| 91 |
+
print(f" After iteration: {i+1} number of pairs: {len(pairs)}")
|
| 92 |
+
|
| 93 |
+
if not pairs:
|
| 94 |
+
break
|
| 95 |
+
|
| 96 |
+
# Find most frequent pair
|
| 97 |
+
best_pair = max(pairs.items(), key=lambda x: x[1])
|
| 98 |
+
if best_pair[1] < min_freq:
|
| 99 |
+
break
|
| 100 |
+
|
| 101 |
+
pair = best_pair[0]
|
| 102 |
+
new_token = ''.join(pair)
|
| 103 |
+
vocab.add(new_token)
|
| 104 |
+
#print("merging ..", pair)
|
| 105 |
+
#print(len(vocab))
|
| 106 |
+
# Record the merge operation
|
| 107 |
+
self.merges[pair] = new_token
|
| 108 |
+
|
| 109 |
+
# Merge the pair in all words
|
| 110 |
+
words = self._merge_vocab(words, pair)
|
| 111 |
+
|
| 112 |
+
# Build final vocabulary
|
| 113 |
+
self.vocab = {**self.special_tokens}
|
| 114 |
+
idx = len(self.special_tokens)
|
| 115 |
+
for token in sorted(vocab):
|
| 116 |
+
self.vocab[token] = idx
|
| 117 |
+
idx += 1
|
| 118 |
+
|
| 119 |
+
self.inverse_vocab = {v: k for k, v in self.vocab.items()}
|
| 120 |
+
|
| 121 |
+
def encode(self, text: str) -> List[int]:
|
| 122 |
+
"""Encode text using learned BPE merges"""
|
| 123 |
+
|
| 124 |
+
bengali_word_pattern = re.compile(r""" ?[\u0980-\u09FF]+| ?[^\s]+|\s+(?!\S)|\s+""")
|
| 125 |
+
extracted_words = bengali_word_pattern.findall(text)
|
| 126 |
+
|
| 127 |
+
words = [list(word) for word in extracted_words]
|
| 128 |
+
|
| 129 |
+
# Apply merges in order
|
| 130 |
+
for pair, merged in self.merges.items():
|
| 131 |
+
words = self._merge_vocab(words, pair)
|
| 132 |
+
|
| 133 |
+
# Convert to token IDs
|
| 134 |
+
result = []
|
| 135 |
+
for word in words:
|
| 136 |
+
for token in word:
|
| 137 |
+
if token in self.vocab:
|
| 138 |
+
result.append(self.vocab[token])
|
| 139 |
+
else:
|
| 140 |
+
result.append(self.special_tokens['<UNK>'])
|
| 141 |
+
|
| 142 |
+
return result
|
| 143 |
+
|
| 144 |
+
def decode(self, ids: List[int]) -> str:
|
| 145 |
+
"""Decode token IDs back to text"""
|
| 146 |
+
return ''.join(self.inverse_vocab.get(id, '<UNK>') for id in ids)
|
| 147 |
+
|
| 148 |
+
def calculate_compression_ratio(self, text: str) -> float:
|
| 149 |
+
"""Calculate compression ratio"""
|
| 150 |
+
encoded = self.encode(text)
|
| 151 |
+
return len(text) / len(encoded)
|
| 152 |
+
|
| 153 |
+
def save(self, path: str) -> None:
|
| 154 |
+
"""Save tokenizer state"""
|
| 155 |
+
# Convert tuple keys to strings for JSON serialization
|
| 156 |
+
serializable_merges = {f"{first}|{second}": merged
|
| 157 |
+
for (first, second), merged in self.merges.items()}
|
| 158 |
+
|
| 159 |
+
data = {
|
| 160 |
+
'vocab': self.vocab,
|
| 161 |
+
'merges': serializable_merges,
|
| 162 |
+
'vocab_size': self.vocab_size,
|
| 163 |
+
'special_tokens': self.special_tokens
|
| 164 |
+
}
|
| 165 |
+
with open(path, 'w', encoding='utf-8') as f:
|
| 166 |
+
json.dump(data, f, ensure_ascii=False, indent=2)
|
| 167 |
+
|
| 168 |
+
@classmethod
|
| 169 |
+
def load(cls, path: str) -> 'BengaliBPETokenizer':
|
| 170 |
+
"""Load tokenizer from file"""
|
| 171 |
+
with open(path, 'r', encoding='utf-8') as f:
|
| 172 |
+
data = json.load(f)
|
| 173 |
+
|
| 174 |
+
tokenizer = cls(vocab_size=data['vocab_size'])
|
| 175 |
+
tokenizer.vocab = data['vocab']
|
| 176 |
+
|
| 177 |
+
# Convert string keys back to tuples
|
| 178 |
+
tokenizer.merges = {tuple(k.split('|')): v
|
| 179 |
+
for k, v in data['merges'].items()}
|
| 180 |
+
|
| 181 |
+
tokenizer.special_tokens = data['special_tokens']
|
| 182 |
+
tokenizer.inverse_vocab = {v: k for k, v in tokenizer.vocab.items()}
|
| 183 |
+
return tokenizer
|