Add model documentation and training vocabulary

README.md

@@ -0,0 +1,388 @@
+---
+language:
+  - prs
+license: apache-2.0
+library_name: transformers
+pipeline_tag: fill-mask
+base_model: HooshvareLab/bert-base-parsbert-uncased
+base_model_relation: finetune
+tags:
+  - dari
+  - dari-persian
+  - persian
+  - parsbert
+  - bert
+  - masked-language-model
+  - masked-lm
+  - nlp
+  - natural-language-processing
+  - low-resource-language
+---
+
+# DariBERT
+
+**A Dari-focused fine-tuned version of ParsBERT.**
+
+DariBERT is an experimental fine-tuned version of
+[`HooshvareLab/bert-base-parsbert-uncased`](https://huggingface.co/HooshvareLab/bert-base-parsbert-uncased),
+adapted toward Dari vocabulary and usage through fine-tuning on a manually curated
+Dari–Persian vocabulary dataset.
+
+The goal of the project is to explore whether an existing Persian-language BERT
+model can be adapted toward Dari-specific vocabulary and linguistic usage using
+a relatively small, manually curated dataset.
+
+> **DariBERT v1.0 is an experimental research and learning project.**
+> It should not be considered a fully trained Dari language model or a replacement
+> for a large-scale pretrained Dari NLP model.
+
+---
+
+## Model Details
+
+### Model Description
+
+| Property | Value |
+|---|---|
+| Model name | DariBERT |
+| Version | v1.0 |
+| Architecture | BERT / Masked Language Model |
+| Base model | HooshvareLab/bert-base-parsbert-uncased |
+| Primary task | Masked Language Modeling |
+| Pipeline | `fill-mask` |
+| Language focus | Dari |
+| Fine-tuning dataset | 211 manually curated Dari–Persian vocabulary entries |
+| Unique Dari entries | 207 |
+| Unique Persian entries | 204 |
+| License | Apache-2.0 |
+
+DariBERT retains the underlying ParsBERT architecture and tokenizer and is
+fine-tuned rather than trained from scratch.
+
+---
+
+## Motivation
+
+Dari and Persian share a large amount of vocabulary and linguistic structure,
+but Dari also contains vocabulary, expressions, pronunciations, and usage that
+can differ from contemporary Iranian Persian.
+
+This project began as an exploration of whether a Persian-language BERT model
+could be nudged toward Dari usage by introducing a curated collection of
+Dari-specific vocabulary and corresponding Persian equivalents.
+
+The project is intentionally small in scope.
+
+Rather than attempting to train a new language model from scratch, DariBERT
+uses an existing Persian pretrained model as its foundation and investigates
+what can be achieved through targeted fine-tuning with a small amount of
+Dari-focused data.
+
+---
+
+## Training Data
+
+The v1.0 training dataset consists of **211 manually curated vocabulary
+entries**, representing **207 unique Dari entries** and **204 unique Persian
+equivalents**.
+
+The vocabulary was manually reviewed and organized into 24 broad categories:
+
+- Basic Communication
+- Household Items
+- Family & Social
+- Food & Cooking
+- Fruits & Vegetables
+- Animals
+- Technology & Modern Terms
+- Medical & Health
+- Clothing & Appearance
+- Administrative & Social
+- Occupations & Trades
+- Building & Architecture
+- Agriculture & Farming
+- Tools & Implements
+- Nature & Geography
+- Adjectives & Descriptors
+- Verbs & Actions
+- Time & Seasons
+- Body Parts
+- Emotions & States
+- Money & Commerce
+- Measurement Units
+- Miscellaneous Important Words
+
+The training vocabulary is provided separately as a CSV file:
+
+`dariBERT_v1_training_vocabulary.csv`
+
+Each entry contains:
+
+```text
+dari,persian,english
+
+The dataset is a manually curated research dataset and is not intended to
+represent the full Dari language.
+
+Training Procedure
+
+DariBERT was fine-tuned from the ParsBERT base model using the Hugging Face
+Transformers library.
+
+The training objective was Masked Language Modeling (MLM).
+
+The model was trained on the Dari entries from the curated vocabulary dataset,
+with the corresponding text tokenized using the ParsBERT tokenizer.
+
+Training configuration
+
+The v1.0 training run used:
+
+Base model: HooshvareLab/bert-base-parsbert-uncased
+Training epochs: 3
+Batch size: 1
+Learning rate: 5e-5
+Weight decay: 0.01
+Maximum sequence length: 16 tokens
+Training objective: Masked Language Modeling
+Hardware: CPU
+Mixed precision: disabled
+
+The training was intentionally lightweight and designed as an experiment in
+Dari-specific adaptation rather than large-scale pretraining.
+
+Intended Use
+
+DariBERT is intended for experimentation and research involving Dari NLP,
+including:
+
+Masked-token prediction
+Vocabulary exploration
+Dari/Persian lexical comparison
+Experimentation with low-resource language adaptation
+Educational NLP experimentation
+Further fine-tuning for downstream Dari NLP tasks
+
+For example, a user can provide a sentence containing a [MASK] token and ask
+the model to predict likely replacements.
+
+Usage
+
+DariBERT can be loaded using the Hugging Face Transformers library.
+
+Installation
+pip install transformers torch
+Masked-token prediction
+from transformers import AutoTokenizer, AutoModelForMaskedLM, pipeline
+
+model_id = "hahang/DariBERT"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForMaskedLM.from_pretrained(model_id)
+
+fill_mask = pipeline(
+    "fill-mask",
+    model=model,
+    tokenizer=tokenizer
+)
+
+text = "من دیروز به بازار رفتم و یک [MASK] خریدم."
+
+results = fill_mask(text)
+
+for result in results:
+    print(
+        result["sequence"],
+        result["score"]
+    )
+
+Example output may look like:
+
+من دیروز به بازار رفتم و یک لپتاپ خریدم.
+من دیروز به بازار رفتم و یک تبلت خریدم.
+من دیروز به بازار رفتم و یک ماشین خریدم.
+
+The exact predictions and scores may vary depending on the Transformers
+version and runtime environment.
+
+Example
+Input
+این کتاب بسیار [MASK] است.
+Example predictions
+
+The fine-tuned model produced predictions including:
+
+این کتاب بسیار خوب است.
+این کتاب بسیار خوبی است.
+این کتاب بسیار ارزشمند است.
+این کتاب بسیار جالب است.
+این کتاب بسیار مهم است.
+
+Another test used:
+
+هوا امروز خیلی [MASK] است.
+
+The model produced predictions including:
+
+هوا امروز خیلی گرم است.
+هوا امروز خیلی سرد است.
+هوا امروز خیلی خوب است.
+هوا امروز خیلی خنک است.
+
+These examples demonstrate that the model can perform masked-token prediction,
+but they should not be interpreted as a formal benchmark.
+
+Evaluation
+
+DariBERT v1.0 was evaluated through qualitative inference tests rather than a
+formal held-out benchmark.
+
+Testing included manually constructed Dari sentences covering areas such as:
+
+Everyday activities
+Shopping
+Descriptive language
+Weather
+Vocabulary usage
+
+The model demonstrated meaningful masked-token predictions in several examples.
+
+However, the small size of the fine-tuning dataset means that these results
+should be considered preliminary.
+
+No formal accuracy, F1, perplexity, or downstream-task benchmark is provided
+for v1.0.
+
+Future versions may include a dedicated held-out Dari evaluation dataset and
+quantitative benchmarks.
+
+Limitations
+
+DariBERT v1.0 has significant limitations.
+
+Small training dataset
+
+The model was fine-tuned using only 211 manually curated vocabulary entries.
+This is extremely small compared with the datasets normally used to train
+modern language models.
+
+Not trained from scratch
+
+DariBERT is not an independently pretrained Dari language model. It is a
+fine-tuned version of ParsBERT.
+
+The underlying model therefore retains substantial characteristics of its
+Persian-language pretraining.
+
+Limited Dari coverage
+
+The vocabulary included in v1.0 represents only a small portion of the Dari
+language.
+
+Many Dari words, expressions, grammatical constructions, dialectal variants,
+and contextual usages are not represented.
+
+No translation capability
+
+DariBERT is not a Dari-to-English or English-to-Dari translation model.
+
+It should not be used as a translation system.
+
+Not an autoregressive text-generation model
+
+DariBERT is a BERT-style masked language model.
+
+Its primary intended operation is predicting masked tokens within text rather
+than generating long passages autoregressively like GPT-style language models.
+
+Limited evaluation
+
+The current version has not been evaluated against a large, independent Dari
+test set.
+
+Relationship to ParsBERT
+
+DariBERT is derived from:
+
+HooshvareLab/bert-base-parsbert-uncased
+
+ParsBERT is a Persian-language BERT model developed for Persian natural
+language processing.
+
+DariBERT does not replace or compete with ParsBERT. Instead, this project
+explores a small-scale adaptation of ParsBERT toward Dari vocabulary and usage.
+
+Please refer to the original ParsBERT model and its documentation for
+information about the underlying architecture, pretraining data, and original
+model development.
+
+Dataset
+
+The manually curated v1.0 vocabulary is included with the project as:
+
+dariBERT_v1_training_vocabulary.csv
+
+The dataset contains three columns:
+
+dari
+persian
+english
+
+The CSV is provided primarily for transparency and reproducibility.
+
+Future Work
+
+Possible future versions of DariBERT may include:
+
+A substantially larger Dari vocabulary
+More naturally occurring Dari sentences
+Curated Dari text corpora
+Improved coverage of Dari-specific grammar and syntax
+Additional dialectal and regional vocabulary
+A dedicated Dari evaluation dataset
+Quantitative benchmarking
+Comparison against the original ParsBERT model
+Further fine-tuning for downstream NLP tasks
+Investigation of Dari-specific tokenization
+Exploration of larger pretrained multilingual or Persian-language models
+
+The long-term goal is to investigate practical approaches for improving
+open-source NLP resources for Dari.
+
+Citation
+
+If you use DariBERT in your research, experiments, or projects, please cite
+this repository:
+
+Ahang, Hamid. DariBERT: A Dari-focused fine-tuned version of ParsBERT.
+2026.
+
+The underlying ParsBERT model should also be appropriately acknowledged when
+DariBERT is used.
+
+License
+
+DariBERT v1.0 is released under the Apache License 2.0.
+
+See the Apache License 2.0 text for the complete terms and conditions.
+
+This model is derived from the ParsBERT model and users should also review the
+license and attribution requirements associated with the original model.
+
+Acknowledgments
+
+This project builds upon the open-source Persian NLP ecosystem and, in
+particular, the ParsBERT model developed by HooshvareLab.
+
+Special thanks to the developers and researchers who have contributed to
+open-source Persian and Dari natural language processing resources.
+
+Project Status
+
+DariBERT v1.0 — Experimental / Initial Release
+
+This release represents an initial exploration of adapting ParsBERT toward
+Dari using a small manually curated vocabulary.
+
+The project is intended to remain open for experimentation, evaluation, and
+future improvement.

dariBERT_v1_training_vocabulary.csv

@@ -0,0 +1,212 @@
+dari,persian,english
+لیکن,اما,but
+نخیر,خیر,no
+تشکر,متشکرم,thank you
+قابل نیست,خواهش می‌کنم,you're welcome
+تبریک باشد,تبریک می‌گویم,congratulations
+چراکه,زیرا,because
+اذخاتر,زیرا,because
+همی,همین,this/that
+کدامه,کدام,which one
+واسه,برای,for
+بچیم,پسرم,my son
+می‌باشه,هست,is / exists
+می‌باشند,هستند,are
+چوکی,صندلی,chair
+پاک کن,پاک کننده,eraser
+توشک,تشک,mattress
+بالشت,بالش,pillow
+چادر شب,ملحفه,bedsheet
+پیاله,استکان,tea cup
+چمچه,قاشق,spoon
+کارد,چاقو,knife
+بادله,سطل,bucket
+تابه,ماهی تابه,frying pan
+کراحی,ماهی تابه,frying pan
+مومبتی,شمع,candle
+دوشی,شانه,comb
+تلیفون,تلفن,telephone
+قاپ,بشقاب,plate
+لَیلَم,پیاله,teacup (smaller/local variant)
+چپلی,دمپایی,slippers
+خلته,کیسه,sack/bag
+فامیل,خانواده,family
+پدرکلان,پدربزرگ,grandfather
+مادرکلان,مادربزرگ,grandmother
+رفیق,دوست,buddy/friend
+کاکا,عمو,uncle
+بچه‌گی,کودکی,childhood
+ماما,دایی,uncle (mother’s brother)
+چپاول,غارت,plunder
+کچالو,سیب زمینی,potato
+بادرنگ,خیار,cucumber
+زردک,هویج,carrot
+بادنجانرومی,گوجه فرنگی,tomato
+مرچ,فلفل,pepper
+قند,شکر,sugar
+مسکه,کره,butter
+قیماق,خامه,cream
+پلو,برنج پخته,cooked rice
+گندمینه,آرد سفید,white flour
+هریسه,آرد درسته,coarse wheat flour
+شوربا,سوپ,soup
+قورمه,خورش,stew
+قابلی پلو,پلو افغانی,kabuli pilaf
+بولانی,نان پرشده,stuffed flatbread
+منتو,مانتی,dumplings
+آشک,گوشتابه,afghan ravioli
+قروت,کشک,dried yogurt
+جلبی,بامیه,jalebi/sweet
+بورانی بادنجان,خورش بادمجان,eggplant stew
+منتو,دست‌پیچ بخارپز,dumpling
+آشک,پیراشکی بخارپز,stuffed dumpling
+ناک,گلابی,pear
+تربوز,هندوانه,watermelon
+آلوچه,گوجه سبز,green plum
+آلوبخارا,آلو,plum
+شبت,شوید,dill
+چمن,چمنزار,lawn/grass
+پیشک,گربه,cat
+گاو,گاو نر,bull
+دومبه,میش,ram/fat-tailed sheep
+سنگپثته,لاک پشت,turtle
+رمه,گله,flock
+بایسکل,دوچرخه,bicycle
+موتر,ماشین,car
+موتر سایکل,موتور سیکلت,motorcycle
+سرویس,اتوبوس,bus
+لاری,کامیون,truck
+کمپیوتر,رایانه,computer
+سافتویر,نرم افزار,software
+هاردویر,سخت افزار,hardware
+ویندوز,پنجره های رایانه,windows OS
+پروسیسر,پردازنده,processor
+موبایل,تلفن همراه,mobile phone
+ایمیل,پست الکترونیکی,email
+دانلود,بارگیری,download
+آپلود,بارگذاری,upload
+فایل,پرونده,file
+فولدر,پوشه,folder
+پرینتر,چاپگر,printer
+اسکنر,پویشگر,scanner
+کیبورد,صفحه کلید,keyboard
+ماوس,موشواره,mouse
+مانیتور,نمایشگر,monitor
+چارجر,شارژر,charger
+کامره,دوربین,camera
+یو اس بی,حافظه فلش,USB
+پروگرام,برنامه,program/software
+چارج,شارژ,charge (as in battery)
+تلویزیونک,تلویزیون,small television
+مخابره,ارتباط بی‌سیم,radio/communication
+داکتر,دکتر,doctor
+شفاخانه,بیمارستان,hospital
+کلینیک,درمانگاه,clinic
+پچکاری,تزریق,injection
+اکسری,عکس رادیولوژی,x-ray
+جراحی,عمل جراحی,operation
+دوا,دارو,medicine
+مریز,بیمار,sick/patient
+تو,تب,fever
+خنک,سرماخوردگی,cold
+چپن,قبای بلند,long coat/chapan
+پتلون,شلوار,trousers
+پرهن,لباس,dress
+لنگی,لنگوتی,waistcloth
+چپلس,دمپایی,slippers
+بوتا,کفش,shoes
+چادر,روسری,headscarf / shawl
+تکه,پارچه,cloth / fabric
+واسکت,جلیقه,vest
+والی,فرماندار,governor
+ملا,آخوند,cleric
+مولوی,عالم دینی,religious scholar
+حاجی,زائر,pilgrim
+خان,آقا,lord/sir
+رئیس,بزرگ,chief
+میر,رئیس قوم,tribal chief
+عسکر,سرباز,soldier
+سرحد,مرز,border
+ولسوالی,بخش,district
+قریه,ده,village
+دکان,مغازه,shop
+کاروان سرای,مسافرخانه,caravanserai/inn
+هوتل,هتل,hotel
+رستورانت,رستوران,restaurant
+میدانحوایی,فرودگاه,airport
+پاسپورت,گذرنامه,passport
+ویزه,روادید,visa
+تاپه,مهر,seal/stamp
+دهقان,کشاورز,farmer
+موچی,کفاش,cobbler
+قالینباف,قالیباف,carpet weaver
+جولاها,بافنده,weaver
+رنگرز,رنگساز,dyer
+سراچه,مسگری,coppersmith
+آهنګر,آهنگر,blacksmith
+زرګر,زرگر,goldsmith
+درایور,راننده,driver
+استاد,معلم,teacher/master
+ملک,مالک,owner
+سوداگر,تاجر,trader
+صحن,حیاط,courtyard
+دالان,راهرو,corridor
+دروازه,در بزرگ,gate
+لنگر,لنگه در,door leaf
+تاقچه,قفسه,shelf
+تکیه,خانقاه,sufi lodge
+زیارت,امامزاده,shrine
+مزار,آرامگاه,tomb
+کلکین,پنجره,window
+دهلیز,راهرو,hallway / corridor
+کاریز,قنات,underground canal
+جوی,جویبار,irrigation channel
+کشتزار,زمین کشاورزی,farmland
+بوستان,باغ میوه,orchard
+گلزار,باغ گل,flower garden
+خرمن,کلوخ,threshing floor
+سرگین,کود,manure
+خوساک,فضولات حیوان,animal dung
+ریسمان,طناب,rope
+چوبک,چوب کوچک,small stick
+صحرا,بیابان,desert
+رود,رودخانه,river
+دریا,رود بزرگ,large river
+چمچمه,چشمه کوچک,small spring
+گل,لجن,mud (sticky)
+جوی,رودخانه,river/stream (small)
+چالاک,زیرک,clever
+خنک,سرد,cool
+کلان,بزرگ,big/great
+زیات,زیاد,many/much
+غریب,فقیر,poor
+پریشان,نگران,worried/upset
+تر,خیس,wet
+سُست,ضعیف,soft/weak
+زُود,سریع,quick
+بیخی,کاملاً,completely
+چُرت,خواب‌آلود,sleepy / drowsy
+بچگانه,کودکانه,childish / juvenile
+مویه,گریه,crying
+خندا,خنده,laughter
+خنده,لبخند,smile
+حالا,الان,now
+پس,بعد,after/then
+پشت,عقب,behind/back
+روی,بالای,on/on top of
+نزد,پیش,near/at (someone's place)
+شاید,ممکن است,maybe/it is possible
+از قبیل,مثل,such as/like
+چاشت,ظهر,noon/lunch time
+غرمه,عصر,afternoon
+خزان,پاییز,autumn
+کله,سر,head
+مینه,عشق,love
+بدی,کینه,hatred
+پیسې,پول,money
+قیمت,هزینه,cost
+زیان,ضرر,loss
+قرز,بدهی,debt
+سیر,کیلو,unit of weight (7kg)
+جریب,هکتار,unit of land area
+چور,غارت,plunder