| # 🗺️ Roadmap | |
| ## 🧱 Phase 1: Foundation (0-2 months) | |
| - Finalize governance and contribution docs | |
| - Define Pashto text normalization policy | |
| - Prepare data schema and validation checklist | |
| - Publish baseline ASR/TTS experiment templates | |
| ## 📈 Phase 2: Data Scale (2-4 months) | |
| - Community data campaigns (recording + validation) | |
| - Curate and release dataset versions (`v0.1`, `v0.2`) | |
| - Improve metadata quality (speaker, dialect, environment) | |
| ## 🤖 Phase 3: Baseline Models (4-6 months) | |
| - Train and release first open ASR baseline | |
| - Train and release first open TTS baseline | |
| - Publish reproducible training/eval scripts | |
| ## 🧪 Phase 4: Benchmark & Demos (6-9 months) | |
| - Release fixed evaluation benchmark | |
| - Launch public leaderboard (WER/CER + TTS quality eval) | |
| - Integrate models into desktop/app demos | |
| ## 🌱 Phase 5: Community Maturity (9+ months) | |
| - Regular release cadence | |
| - Contributor mentoring and review rotations | |
| - Long-term maintenance and quality governance | |