TechCrunch · AI· Ivan Mehta·· 8 h ago
Underdog shows off a 32MB speech model in new demo
Underdog shows off a 32MB speech model in new demo
AI summary
Despite its small size, Underdog's new model can generate both speech and music.
Selection record
Threshold 76Media and individualsFirst 58Second 52
Not admittedSum of both 110 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：32MB语音模型及端侧AI演示
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: TechCrunch · AI · techcrunch.com