Pashto Language Resources Hub

pashto-language-resources is a community-led open-source project focused on making Pashto (also written as Pukhto/Pushto) a first-class language in speech and language AI.

👋 Quick Actions

• 🔎 Search technical resources: Pashto Resource Search
• 📄 Search papers: Pashto Papers Search
• 📘 Browse docs: Documentation Hub
• 📦 Browse verified catalog guide: resource_catalog.md

🎯 Mission

• Build open Pashto datasets and resource indexes for ASR, TTS, NLP, and MT.
• Publish reproducible baseline models, benchmark schemas, and evaluation workflows.
• Keep progress transparent, contributor-friendly, and public-benefit oriented.

🧠 Intent Pages

• Pashto datasets: pashto_datasets.md
• Pashto ASR resources: pashto_asr.md
• Pashto TTS resources: pashto_tts.md

🗂️ Repository References

• Repository: Musawer1214/pashto-language-resources
• Hugging Face: Musawer14/pashto-language-resources
• Purpose: PROJECT_PURPOSE.md
• Roadmap: ROADMAP.md
• Contributing: CONTRIBUTING.md

📈 SEO Operations

• Discoverability playbook: discoverability_seo.md
• GitHub topics checklist: github_topics_checklist.md
• Backlink strategy: backlink_strategy.md

🧾 Releases

• Release notes index: releases/README.md
• Current release notes: v1.2.1
• Changelog: ../CHANGELOG.md

🤝 Contribution

You can help by improving documentation, validating normalization rows, sharing verified resources, or contributing data, model, and evaluation workflows.

Start here:

• docs/README.md
• community/COMMUNICATION.md

⚖️ License

This project is released under Apache 2.0. See LICENSE.