DariBERT

A Dari-focused fine-tuned version of ParsBERT.

DariBERT is an experimental fine-tuned version of 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.

Dari and Farsi are two varieties of Persian, with Dari being the main language of Afghanistan and Farsi primarily spoken in Iran.

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 (Also see full list below)

Each entry contains:

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 پیراهن خریدم.
من دیروز به بازار رفتم و یک بالثت خریدم.
من دیروز به بازار رفتم و یک دسته گل 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 دراز است.
این کتاب بسیار جالب است.
این کتاب بسیار مهم است.

This example 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.


List of added Dari words and their corresponding Persian/English translation:

# ===== BASIC COMMUNICATION =====
"dari": "لیکن", "persian": "اما", "english": "but"
"dari": "نخیر", "persian": "خیر", "english": "no"
"dari": "تشکر", "persian": "متشکرم", "english": "thank you"
"dari": "قابل نیست", "persian": "خواهش می‌کنم", "english": "you're welcome"
"dari": "تبریک باشد", "persian": "تبریک می‌گویم", "english": "congratulations"
"dari": "چراکه", "persian": "زیرا", "english": "because"
"dari": "اذخاتر", "persian": "زیرا", "english": "because"
"dari": "همی", "persian": "همین", "english": "this/that"
"dari": "کدامه", "persian": "کدام", "english": "which one"
"dari": "واسه", "persian": "برای", "english": "for"
"dari": "بچیم", "persian": "پسرم", "english": "my son"
"dari": "می‌باشه", "persian": "هست", "english": "is / exists"
"dari": "می‌باشند", "persian": "هستند", "english": "are"
    
# ===== HOUSEHOLD ITEMS (HIGH-FREQUENCY) =====
"dari": "چوکی", "persian": "صندلی", "english": "chair"
"dari": "پاک کن", "persian": "پاک کننده", "english": "eraser"
"dari": "توشک", "persian": "تشک", "english": "mattress"
"dari": "بالشت", "persian": "بالش", "english": "pillow"
"dari": "چادر شب", "persian": "ملحفه", "english": "bedsheet"
"dari": "پیاله", "persian": "استکان", "english": "tea cup"
"dari": "چمچه", "persian": "قاشق", "english": "spoon"
"dari": "کارد", "persian": "چاقو", "english": "knife"
"dari": "بادله", "persian": "سطل", "english": "bucket"
"dari": "تابه", "persian": "ماهی تابه", "english": "frying pan"
"dari": "کراحی", "persian": "ماهی تابه", "english": "frying pan"
"dari": "مومبتی", "persian": "شمع", "english": "candle"
"dari": "دوشی", "persian": "شانه", "english": "comb"
"dari": "تلیفون", "persian": "تلفن", "english": "telephone"
"dari": "قاپ", "persian": "بشقاب", "english": "plate"
"dari": "لَیلَم", "persian": "پیاله", "english": "teacup (smaller/local variant)"
"dari": "چپلی", "persian": "دمپایی", "english": "slippers"
"dari": "خلته", "persian": "کیسه", "english": "sack/bag"

# ===== FAMILY & SOCIAL =====
"dari": "فامیل", "persian": "خانواده", "english": "family"
"dari": "پدرکلان", "persian": "پدربزرگ", "english": "grandfather"
"dari": "مادرکلان", "persian": "مادربزرگ", "english": "grandmother"
"dari": "رفیق", "persian": "دوست", "english": "buddy/friend"
"dari": "کاکا", "persian": "عمو", "english": "uncle"
"dari": "بچه‌گی", "persian": "کودکی", "english": "childhood"
"dari": "ماما", "persian": "دایی", "english": "uncle (mother’s brother)"
    
# ===== FOOD & COOKING (HIGH-FREQUENCY) =====
"dari": "چپاول", "persian": "غارت", "english": "plunder"
"dari": "کچالو", "persian": "سیب زمینی", "english": "potato"
"dari": "بادرنگ", "persian": "خیار", "english": "cucumber"
"dari": "زردک", "persian": "هویج", "english": "carrot"
"dari": "بادنجانرومی", "persian": "گوجه فرنگی", "english": "tomato"
"dari": "مرچ", "persian": "فلفل", "english": "pepper"
"dari": "قند", "persian": "شکر", "english": "sugar"
"dari": "مسکه", "persian": "کره", "english": "butter"
"dari": "قیماق", "persian": "خامه", "english": "cream"
"dari": "پلو", "persian": "برنج پخته", "english": "cooked rice"
"dari": "گندمینه", "persian": "آرد سفید", "english": "white flour"
"dari": "هریسه", "persian": "آرد درسته", "english": "coarse wheat flour"
"dari": "شوربا", "persian": "سوپ", "english": "soup"
"dari": "قورمه", "persian": "خورش", "english": "stew"
"dari": "قابلی پلو", "persian": "پلو افغانی", "english": "kabuli pilaf"
"dari": "بولانی", "persian": "نان پرشده", "english": "stuffed flatbread"
"dari": "منتو", "persian": "مانتی", "english": "dumplings"
"dari": "آشک", "persian": "گوشتابه", "english": "afghan ravioli"
"dari": "قروت", "persian": "کشک", "english": "dried yogurt"
"dari": "جلبی", "persian": "بامیه", "english": "jalebi/sweet"
"dari": "بورانی بادنجان", "persian": "خورش بادمجان", "english": "eggplant stew"
"dari": "منتو", "persian": "دست‌پیچ بخارپز", "english": "dumpling"
"dari": "آشک", "persian": "پیراشکی بخارپز", "english": "stuffed dumpling"

    
# ===== FRUITS & VEGETABLES =====
"dari": "ناک", "persian": "گلابی", "english": "pear"
"dari": "تربوز", "persian": "هندوانه", "english": "watermelon"
"dari": "آلوچه", "persian": "گوجه سبز", "english": "green plum"
"dari": "آلوبخارا", "persian": "آلو", "english": "plum"
"dari": "شبت", "persian": "شوید", "english": "dill"
"dari": "چمن", "persian": "چمنزار", "english": "lawn/grass"
    
# ===== ANIMALS =====
"dari": "پیشک", "persian": "گربه", "english": "cat"
"dari": "گاو", "persian": "گاو نر", "english": "bull"
"dari": "دومبه", "persian": "میش", "english": "ram/fat-tailed sheep"
"dari": "سنگپثته", "persian": "لاک پشت", "english": "turtle"
"dari": "رمه", "persian": "گله", "english": "flock"

    
# ===== TECHNOLOGY & MODERN TERMS (ENGLISH LOANWORDS IN DARI) =====
"dari": "بایسکل", "persian": "دوچرخه", "english": "bicycle"
"dari": "موتر", "persian": "ماشین", "english": "car"
"dari": "موتر سایکل", "persian": "موتور سیکلت", "english": "motorcycle"
"dari": "سرویس", "persian": "اتوبوس", "english": "bus"
"dari": "لاری", "persian": "کامیون", "english": "truck"
"dari": "کمپیوتر", "persian": "رایانه", "english": "computer"
"dari": "سافتویر", "persian": "نرم افزار", "english": "software"
"dari": "هاردویر", "persian": "سخت افزار", "english": "hardware"
"dari": "ویندوز", "persian": "پنجره های رایانه", "english": "windows OS"
"dari": "پروسیسر", "persian": "پردازنده", "english": "processor"
"dari": "موبایل", "persian": "تلفن همراه", "english": "mobile phone"
"dari": "ایمیل", "persian": "پست الکترونیکی", "english": "email"
"dari": "دانلود", "persian": "بارگیری", "english": "download"
"dari": "آپلود", "persian": "بارگذاری", "english": "upload"
"dari": "فایل", "persian": "پرونده", "english": "file"
"dari": "فولدر", "persian": "پوشه", "english": "folder"
"dari": "پرینتر", "persian": "چاپگر", "english": "printer"
"dari": "اسکنر", "persian": "پویشگر", "english": "scanner"
"dari": "کیبورد", "persian": "صفحه کلید", "english": "keyboard"
"dari": "ماوس", "persian": "موشواره", "english": "mouse"
"dari": "مانیتور", "persian": "نمایشگر", "english": "monitor"
"dari": "چارجر", "persian": "شارژر", "english": "charger"
"dari": "کامره", "persian": "دوربین", "english": "camera"
"dari": "یو اس بی", "persian": "حافظه فلش", "english": "USB"
"dari": "پروگرام", "persian": "برنامه", "english": "program/software"
"dari": "چارج", "persian": "شارژ", "english": "charge (as in battery)"
"dari": "تلویزیونک", "persian": "تلویزیون", "english": "small television"
"dari": "مخابره", "persian": "ارتباط بی‌سیم", "english": "radio/communication"
    
# ===== MEDICAL & HEALTH =====
"dari": "داکتر", "persian": "دکتر", "english": "doctor"
"dari": "شفاخانه", "persian": "بیمارستان", "english": "hospital"
"dari": "کلینیک", "persian": "درمانگاه", "english": "clinic"
"dari": "پچکاری", "persian": "تزریق", "english": "injection"
"dari": "اکسری", "persian": "عکس رادیولوژی", "english": "x-ray"
"dari": "جراحی", "persian": "عمل جراحی", "english": "operation"
"dari": "دوا", "persian": "دارو", "english": "medicine"
"dari": "مریز", "persian": "بیمار", "english": "sick/patient"
"dari": "تو", "persian": "تب", "english": "fever"
"dari": "خنک", "persian": "سرماخوردگی", "english": "cold"
    
# ===== CLOTHING & APPEARANCE =====
"dari": "چپن", "persian": "قبای بلند", "english": "long coat/chapan"
"dari": "پتلون", "persian": "شلوار", "english": "trousers"
"dari": "پرهن", "persian": "لباس", "english": "dress"
"dari": "لنگی", "persian": "لنگوتی", "english": "waistcloth"
"dari": "چپلس", "persian": "دمپایی", "english": "slippers"
"dari": "بوتا", "persian": "کفش", "english": "shoes"
"dari": "چادر", "persian": "روسری", "english": "headscarf / shawl"
"dari": "تکه", "persian": "پارچه", "english": "cloth / fabric"
"dari": "واسکت", "persian": "جلیقه", "english": "vest"

# ===== ADMINISTRATIVE & SOCIAL =====
"dari": "والی", "persian": "فرماندار", "english": "governor"
"dari": "ملا", "persian": "آخوند", "english": "cleric"
"dari": "مولوی", "persian": "عالم دینی", "english": "religious scholar"
"dari": "حاجی", "persian": "زائر", "english": "pilgrim"
"dari": "خان", "persian": "آقا", "english": "lord/sir"
"dari": "رئیس", "persian": "بزرگ", "english": "chief"
"dari": "میر", "persian": "رئیس قوم", "english": "tribal chief"
"dari": "عسکر", "persian": "سرباز", "english": "soldier"
"dari": "سرحد", "persian": "مرز", "english": "border"
"dari": "ولسوالی", "persian": "بخش", "english": "district"
"dari": "قریه", "persian": "ده", "english": "village"
"dari": "دکان", "persian": "مغازه", "english": "shop"
"dari": "کاروان سرای", "persian": "مسافرخانه", "english": "caravanserai/inn"
"dari": "هوتل", "persian": "هتل", "english": "hotel"
"dari": "رستورانت", "persian": "رستوران", "english": "restaurant"
"dari": "میدانحوایی", "persian": "فرودگاه", "english": "airport"
"dari": "پاسپورت", "persian": "گذرنامه", "english": "passport"
"dari": "ویزه", "persian": "روادید", "english": "visa"
"dari": "تاپه", "persian": "مهر", "english": "seal/stamp"

# ===== OCCUPATIONS & TRADES =====
"dari": "دهقان", "persian": "کشاورز", "english": "farmer"
"dari": "موچی", "persian": "کفاش", "english": "cobbler"
"dari": "قالینباف", "persian": "قالیباف", "english": "carpet weaver"
"dari": "جولاها", "persian": "بافنده", "english": "weaver"
"dari": "رنگرز", "persian": "رنگساز", "english": "dyer"
"dari": "سراچه", "persian": "مسگری", "english": "coppersmith"
"dari": "آهنګر", "persian": "آهنگر", "english": "blacksmith"
"dari": "زرګر", "persian": "زرگر", "english": "goldsmith"
"dari": "درایور", "persian": "راننده", "english": "driver"
"dari": "استاد", "persian": "معلم", "english": "teacher/master"
"dari": "ملک", "persian": "مالک", "english": "owner"
"dari": "سوداگر", "persian": "تاجر", "english": "trader"

# ===== BUILDING & ARCHITECTURE =====
"dari": "صحن", "persian": "حیاط", "english": "courtyard"
"dari": "دالان", "persian": "راهرو", "english": "corridor"
"dari": "دروازه", "persian": "در بزرگ", "english": "gate"
"dari": "لنگر", "persian": "لنگه در", "english": "door leaf"
"dari": "تاقچه", "persian": "قفسه", "english": "shelf"
"dari": "تکیه", "persian": "خانقاه", "english": "sufi lodge"
"dari": "زیارت", "persian": "امامزاده", "english": "shrine"
"dari": "مزار", "persian": "آرامگاه", "english": "tomb"
"dari": "کلکین", "persian": "پنجره", "english": "window"
"dari": "دهلیز", "persian": "راهرو", "english": "hallway / corridor"

# ===== AGRICULTURE & FARMING =====
"dari": "کاریز", "persian": "قنات", "english": "underground canal"
"dari": "جوی", "persian": "جویبار", "english": "irrigation channel"
"dari": "کشتزار", "persian": "زمین کشاورزی", "english": "farmland"
"dari": "بوستان", "persian": "باغ میوه", "english": "orchard"
"dari": "گلزار", "persian": "باغ گل", "english": "flower garden"
"dari": "خرمن", "persian": "کلوخ", "english": "threshing floor"
"dari": "سرگین", "persian": "کود", "english": "manure"
"dari": "خوساک", "persian": "فضولات حیوان", "english": "animal dung"

# ===== TOOLS & IMPLEMENTS =====
"dari": "ریسمان", "persian": "طناب", "english": "rope"
"dari": "چوبک", "persian": "چوب کوچک", "english": "small stick"

# ===== NATURE & GEOGRAPHY =====
"dari": "صحرا", "persian": "بیابان", "english": "desert"
"dari": "رود", "persian": "رودخانه", "english": "river"
"dari": "دریا", "persian": "رود بزرگ", "english": "large river"
"dari": "چمچمه", "persian": "چشمه کوچک", "english": "small spring"
"dari": "گل", "persian": "لجن", "english": "mud (sticky)"
"dari": "جوی", "persian": "رودخانه", "english": "river/stream (small)"

# ===== ADJECTIVES & DESCRIPTORS =====
"dari": "چالاک", "persian": "زیرک", "english": "clever"
"dari": "خنک", "persian": "سرد", "english": "cool"
"dari": "کلان", "persian": "بزرگ", "english": "big/great"
"dari": "زیات", "persian": "زیاد", "english": "many/much"
"dari": "غریب", "persian": "فقیر", "english": "poor"
"dari": "پریشان", "persian": "نگران", "english": "worried/upset"
"dari": "تر", "persian": "خیس", "english": "wet"
"dari": "سُست", "persian": "ضعیف", "english": "soft/weak"
"dari": "زُود", "persian": "سریع", "english": "quick"
"dari": "بیخی", "persian": "کاملاً", "english": "completely"
"dari": "چُرت", "persian": "خواب‌آلود", "english": "sleepy / drowsy"
"dari": "بچگانه", "persian": "کودکانه", "english": "childish / juvenile"

# ===== VERBS & ACTIONS =====
"dari": "مویه", "persian": "گریه", "english": "crying"
"dari": "خندا", "persian": "خنده", "english": "laughter"
"dari": "خنده", "persian": "لبخند", "english": "smile"
"dari": "حالا", "persian": "الان", "english": "now"
"dari": "پس", "persian": "بعد", "english": "after/then"
"dari": "پشت", "persian": "عقب", "english": "behind/back"
"dari": "روی", "persian": "بالای", "english": "on/on top of"
"dari": "نزد", "persian": "پیش", "english": "near/at (someone's place)"
"dari": "شاید", "persian": "ممکن است", "english": "maybe/it is possible"
"dari": "از قبیل", "persian": "مثل", "english": "such as/like"

# ===== TIME & SEASONS =====
"dari": "چاشت", "persian": "ظهر", "english": "noon/lunch time"
"dari": "غرمه", "persian": "عصر", "english": "afternoon"
"dari": "خزان", "persian": "پاییز", "english": "autumn"

# ===== BODY PARTS =====
"dari": "کله", "persian": "سر", "english": "head"

# ===== EMOTIONS & STATES =====
"dari": "مینه", "persian": "عشق", "english": "love"
"dari": "بدی", "persian": "کینه", "english": "hatred"

# ===== MONEY & COMMERCE =====
"dari": "پیسې", "persian": "پول", "english": "money"
"dari": "قیمت", "persian": "هزینه", "english": "cost"
"dari": "زیان", "persian": "ضرر", "english": "loss"
"dari": "قرز", "persian": "بدهی", "english": "debt"

# ===== MEASUREMENT UNITS =====
"dari": "سیر", "persian": "کیلو", "english": "unit of weight (7kg)"
"dari": "جریب", "persian": "هکتار", "english": "unit of land area"

# ===== MISCELLANEOUS IMPORTANT WORDS =====
"dari": "چور", "persian": "غارت", "english": "plunder"}

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.


Downloads last month
47
Safetensors
Model size
0.2B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for hahang/DariBERT

Finetuned
(25)
this model