Grants:Programs/Wikimedia Community Fund/Rapid Fund/WIkimedia Swahili Trust (ID: 23753690)
Applicant details
[edit]- Main Wikimedia username. (required)
AlvinDulle
- Organization
N/A
- If you are a group or organization leader, board member, president, executive director, or staff member at any Wikimedia group, affiliate, or Wikimedia Foundation, you are required to self-identify and present all roles. (required)
N/A
- Describe all relevant roles with the name of the group or organization and description of the role. (required)
Main proposal
[edit]- 1. State the title of your proposal. This will also be the Meta-Wiki page title.
WIkimedia Swahili Trust
- 2. and 3. Proposed start and end dates for the proposal.
2026-04-08 - 2026-12-31
- 4. What is your tech project about, and how do you plan to build the product?
Include the following points in your answer:
- Project goal and problem you solve
- Product strategy or project roadmap
- Technical approach (infrastructure, tech stack, key tools and services)
- Integrations or dependencies (if any)
Wikimedia Swahili Trust is an AI-powered platform designed to assess and improve the reliability of English-to-Swahili translations on Wikimedia projects. Many Swahili translations currently suffer from inaccuracies that reduce trust and user engagement. Our project will provide automatic trust scoring, highlighting areas that need review, and suggesting improved translations.
The technical approach involves building a web-based tool using Python for AI processing, React.js for the frontend, and Node.js/Express for the backend. We will use open-source NLP models to analyze translations and detect inconsistencies or errors. The system will integrate with Wikimedia APIs to fetch articles and suggest corrections while tracking confidence scores. Key tools include Hugging Face Transformers, FastAPI, and MongoDB for storing translation data.
- 5. What is the expected impact of your project, and how will you measure success?
Include the following points in your answer:
- Milestones and progress tracking
- Project impact and success metrics
''''The project will increase the accuracy and trustworthiness of Swahili Wikimedia articles. Milestones:
- M1: AI translation validation system operational by June 2026
- M2: Beta testing with 50+ Swahili articles by September 2026
- M3: Public launch with community feedback by December 2026
Success metrics include:
- Percentage of articles flagged for review vs. corrected
- User adoption and contributor engagement
- Improvement in translation trust scores over time
- 6. Who is your target audience, and how have you confirmed there is demand for this project? How did you engage with the Wikimedia community?
Include the following points in your answer:
- Project demand and target audience description
- Links to interaction(s) with Wikimedia community
- Evidence from community consultation such as the [Community Wishlist]
The target audience includes Swahili-speaking Wikimedia editors, translators, and readers. Community consultations and discussions on Meta-Wiki and the [Community Wishlist Survey] confirmed a strong demand for tools that ensure translation accuracy and reliability. Contributors frequently report difficulties in verifying translation quality, confirming the need for AI-based support.
- 7. How will your team predict and manage potential user security and privacy risks, and what risks do you currently see?
Include the following points in your answer:
- The level of in-house or consulted security and privacy expertise you will have available to you during delivery of this project
- How your development, testing, and deployment processes mitigate the introduction of unnecessary security or privacy risks
''''We will anonymize all article and user data processed by the AI to maintain privacy. Security measures include: secure API calls, encrypted storage for sensitive data, and limited access controls for admin tools. Current risks include incorrect AI suggestions; we will mitigate these by allowing human review and using confidence scores to indicate reliability.
- 8. Who is on your team, and what is your experience?
Include the following points in your answer:
- Your experience as a developer, relevant past projects
- Wikimedia SUL (developer), Gerrit, Github, Gitlab or other relevant public account handles
- Other team members, their roles and expertise
Kelvin J Dulle (Lead Developer): Full-stack developer with experience in AI, Python, React.js, Node.js, and database management. GitHub: [1]
Project Coordinator: Oversees community engagement and translation validation workflow
AI Consultant: NLP and translation expert responsible for AI model integration
- 9. How will the project be maintained long-term?
Include the long-term maintenance plan with maintainer(s) in your answer. If you expect the long-term maintenance to incur expenses, please list those and the plan for long-term expense coverage.
Maintenance includes:
Periodic AI model updates to improve translation accuracy
Regular bug fixes and security updates
Community-driven reviews and feedback integration
Long-term costs will be supported through future Wikimedia grants and collaborations with academic institutions focused on Swahili language technology.
- 10. Under what license will your code be released, and how will you ensure the product is well documented?
Include the following points in your answer:
- Code license and compatibility with Wikimedia projects
- Documentation plan
Yes, it will use open-source NLP models from Hugging Face and integrate with Wikimedia APIs. Enhancements and code improvements will be contributed back to the open-source community where possible.
- 11. Will your project depend on or contribute to third-party tools or services?
This project directly supports the Wikimedia mission by increasing trust in local language content, ensuring Swahili-speaking users can rely on accurate translations for knowledge consumption and contribution.
- 12. Is there anything else you’d like to share about your project? (optional)
Budget
[edit]- 13. Upload your budget for this proposal or indicate the link to it. (required)
- 14. and 15. What is the amount you are requesting for this proposal? Please provide the amount in your local currency. (required)
1425465.44 TZS
- 16. Convert the amount requested into USD using the Oanda converter. This is done only to help you assess the USD equivalent of the requested amount. Your request should be between 500 - 5,000 USD.
560 USD
- We/I have read the Application Privacy Statement, WMF Friendly Space Policy and Universal Code of Conduct.
Yes
Endorsements and Feedback
[edit]Please add endorsements and feedback to the grant discussion page only. Endorsements added here will be removed automatically.
Community members are invited to share meaningful feedback on the proposal and include reasons why they endorse the proposal. Consider the following:
- Stating why the proposal is important for the communities involved and why they think the strategies chosen will achieve the results that are expected.
- Highlighting any aspects they think are particularly well developed: for instance, the strategies and activities proposed, the levels of community engagement, outreach to underrepresented groups, addressing knowledge gaps, partnerships, the overall budget and learning and evaluation section of the proposal, etc.
- Highlighting if the proposal focuses on any interesting research, learning or innovation, etc. Also if it builds on learning from past proposals developed by the individual or organization, or other Wikimedia communities.
- Analyzing if the proposal is going to contribute in any way to important developments around specific Wikimedia projects or Movement Strategy.
- Analysing if the proposal is coherent in terms of the objectives, strategies, budget, and expected results (metrics).
This is an automatically generated Meta-Wiki page. The page was copied from Fluxx, the web service of Wikimedia Foundation Funds, where the user has submitted their application. Please do not make any changes to this page because all changes will be removed after the next update. Use the discussion page for your feedback. The page was created by CR-FluxxBot.