Underdog shows off Woof, a 32MB speech generation model
What happened
Underdog, which released Bark, a 167MB on-device speech-to-text model for transcription and dictation, a few weeks ago, has now shown a browser game demo built on its new speech generation model Woof. Woof is 32MB with 31 million parameters and is available to download. In the demo, users type into a typewriter in the game and hear the text read aloud, and can turn a dial to generate different music. The company says the model runs on most devices without a network connection.
Written by AI from the coverage · updated 53 minutes ago
Coverage
Follow the reports to see the story from different sides.
- TechCrunch · AIUnderdog shows off a 32MB speech model in new demo
Underdog 推出基于新语音生成模型 Woof 的浏览器游戏演示，该模型大小仅为 32MB，拥有 31 million 参数并开放下载。用户可在游戏中的打字机输入文字并听到朗读，也可旋转调谐器生成不同音乐；公司称模型可在大多数设备上无需联网运行。几周前，Underdog 还推出了面向端侧转录和听写的 167 MB 语音转文字模型 Bark。
Heat over time
Not enough continuous observations to draw a trend yet.