Inworld AI @inworld_ai · 31 Aug 2026
Our Head of ML/AI Research, @altsoph just open-sourced our TTS evaluation toolkit. TTS evaluation is less standardized than people assume. Two teams can run the same model on the same dataset and report different word error rates. The ASR model you measure with moves the number.
3 072Views
53Likes
6Reposts
4Replies
1Quotes
33Bookmarks
Is that a lot?
2.07×vs this author's median1 485 views is typical
75Percentile for this authorof 4 recent posts
1.12×vs 10K–100K median2 751 views is typical
24.98%Reachviews ÷ followers
2.08%Engagement rateof viewers reacted