

Maureen
2K posts







AI listens to everyone. Except for 5.5 billion people. We’re launching BRIDGE (Benchmark of Regional & International Data for Global Evaluation), the first independent Global South ASR benchmark. 22 regional languages across 15 models evaluated on a first-of-its-kind 7-metric stack. Read the full benchmark here: humynlabs.ai/bridge Most ASR benchmarks report one WER per model per language. That number hides more than it reveals. Dialect variation, code-switching fidelity, speaker overlap and script-mismatch all sit underneath it. BRIDGE surfaces them. Here’s how 🧵


















CREAO Builds Contest is live 💰$250 total prize pool 📆 From May 1 → May 8, 10:00 AM UTC This time, we're not only asking what you built. We also want to know what the building experience actually felt like: what worked, what was confusing, what saved you time, and what could be better. Honest, specific feedback matters here as much as the build itself. To participate: 1. Follow @CreaoBuilds on X 2. Build an agent in CREAO 3. Publicly share your build (X post, thread, or demo video) 4. Submit in our Discord and include a short write-up about your experience 5. Quote this post with your agent name/title Build something useful. Tell us what the process felt like. Help shape the next version of CREAO. More details in Discord. discord.gg/creao-ai
