Contribute অবদান রাখুন
Every entry on this site lives as a YAML file in a public GitHub repository. The site rebuilds automatically when a pull request is merged — no CMS, no accounts, just Git.
kishormorol/BanglaNLP-Hub — every resource is one small YAML record under data/datasets/, data/papers/, data/models.yaml, or data/tools.yaml.
Copy the format below and include a link you have actually opened. npm run validate checks the schema, the URL, and the verified date before CI will go green.
A maintainer reviews within about a week. On merge the site rebuilds and your entry goes live.
No invented scores, sizes, licenses, or BibTeX. Every leaderboard row must cite the paper reporting that exact number on that exact benchmark — which is why 9leaderboards still render an empty state. A working link does not prove the metadata is right. If you are unsure about a field, leave it out and say so in the pull request; missing is fine, wrong is not. Full rules in CONTRIBUTING.md.
Entry format
# data/datasets/sentiment.yaml
- id: sentnob # unique, lowercase
name: SentNoB
task: sentiment # must match the filename
size: "15,728 comments" # human-readable
sizeN: 15728 # numeric, used for sorting
license: CC BY-NC-SA 4.0
year: 2021
source: SentNoB (Findings EMNLP 2021)
link: https://github.com/KhondokerIslam/SentNoB
verified: 2026-06-28 # the date YOU opened the link
desc: Sentiment on noisy user comments from news and social platforms.
bibtex: | # optional — omit if none exists upstream
@inproceedings{islam-etal-2021-sentnob, ... }Submit a resource
Not comfortable with Git? Fill this in and we'll turn it into a pull request for you, credited to you.
Prefer to skip the form? Open the Submit a resource issue directly.
Contributors অবদানকারী
Resources suggested by the community. Each paper's full author list is shown as published.
- Automated Bengali Physics MCQ Solver: A Large Language Model Approach with Chain-of-Thought ReasoningMd. Sagor Chowdhury, Adiba Fairooz Chowdhury, Ayesha Banu, Riad Hossain
- BanglaProtha: Evaluating Vision Language Models in Underrepresented Long-tail Cultural ContextsMd Fahim, Md Sakib Ul Rahman, Akm Moshiur Rahman, Md Farhan Ishmam, Md Tasmim Rahman, Fariha Tanjim Shifat, Fabiha Haider, Md Farhad Alam Bhuiyan
- BTTC10,283 messages · CC BY 4.0
- Bangla-WhisperDiar: Fine-Tuning Whisper and PyAnnote for Bangla Long-Form Speech Recognition and Speaker DiarizationMohammed Aman Bhuiyan, Md Sazzad Hossain Adib, Samiul Basir Bhuiyan, Amit Chakraborty, Aritra Islam Saswato, Ahmed Faizul Haque Dhrubo, Mohammad Ashrafuzzaman Khan
- Bengali Emotion Classification from Social Media Text Using Deep Learning and Transformer-Based Models with ExplainabilityMujtahid Alam, Shuhena Salam Aonty, Sha Newaz Mahmud, Nahid Riaz Swachha, Ahmed Talal Wazih
- Bengali Human Sentiment Detection and Classification using Attention based Bidirectional LSTMSha Newaz Mahmud, Nahid Riaz Swachha, Ahmed Talal Wazih, Shuvodwip Saha, Shougata Paul, Shuhena Salam Aonty
- Lipi-Ghor (bn-882-SSTT)882 hrs · CC BY 4.0
- Sanjidh090/moonshine-base-bnMoonshine · 61.5M
- bengaliAI/tugstugi_bengaliai-regional-asr_whisper-mediumWhisper-medium · 0.8B
- hishab/titu_stt_bn_conformer_largeConformer-CTC · ~120M
- Bengali-Loop (ASR corpus)191 recordings / 158.6 hrs · Mixed
- Bengali-Loop: Community Benchmarks for Long-Form Bangla ASR and Speaker DiarizationH. M. Shadman Tabib, Istiak Ahmmed Rifti, Abdullah Muhammed Amimul Ehsan, Somik Dasgupta, Md Zim Mim Siddiqee Sowdha, Abrar Jahin Sarker, Md. Rafiul Islam Nijamy, Tanvir Hossain, Mst. Metaly Khatun, Munzer Mahmood, Rakesh Debnath, Gourab Biswas, Asif Karim, Wahid Al Azad Navid, Masnoon Muztahid, Fuad Ahmed Udoy, Shahad Shahriar Rahman, Md. Tashdiqur Rahman Shifat, Most. Sonia Khatun, Mushfiqur Rahman, Md. Miraj Hasan, Anik Saha, Mohammad Ninad Mahmud Nobo, Soumik Bhattacharjee, Tusher Bhomik, Ahmmad Nur Swapnil, Shahriar Kabir
- BanglaSER1,467 recordings · CC BY 4.0
- KBES (KUET Bangla Emotional Speech)900 recordings · CC BY 4.0
- ALERT4,027 texts · CC BY 4.0
- Bangla-ToCo1,004 comments · CC BY 4.0
- Bangla-MedER2,980 texts · CC BY 4.0
- BABSA15,860 instances · CC BY-NC-SA 4.0
- BanglaSarc312,089 comments · CC BY 4.0
- BanFakeNews-2.060,000 articles · Apache 2.0
- BanglaRegionalTextCorpus4,653 sentences · CC BY 4.0
- Kothon17,300 sentence pairs · CC BY 4.0
- SOMADHAN8,792 problems · CC BY 4.0
- hishab/titulm-llama-3.2-1b-v2.0Llama 3.2 · 1B
- Kothon: A large-scale dataset for machine translation of the Chittagonian and Sylheti dialects into standard BanglaMd. Atique Faisal, Farhan Sadaf, Dipta Chowdhury, H.M. Azrof, Monojit Paul Tanmay
- BanHate19,203 comments · MIT
- BanNERD85,175 sentences · CC BY-NC-ND 4.0
- NCTB-QA87,805 QA pairs · CC BY-NC 4.0
- BanglaSocialBench1,719 instances · CC BY 4.0