view reply Some relevant videos on using Treble10: IR collections with the Treble10 dataset: https://www.youtube.com/watch?v=JUilaDZ3Dlc Audio Scene Generation with the Treble10 dataset: https://www.youtube.com/watch?v=Bub9QjFtreQ
ALARM Collection Official checkpoints and data for "ALARM: Audio–Language Alignment for Reasoning Models" • 8 items • Updated 13 days ago • 1
Running on CPU Upgrade 200 The Synthetic Data Playbook: Generating Trillions of the Finest Tokens 📝 200 Explore synthetic data experiments as an interactive bookshelf
ibm-granite/granite-4.0-1b-speech Automatic Speech Recognition • 2B • Updated 5 days ago • 34.2k • 172
Music Flamingo: Scaling Music Understanding in Audio Language Models Paper • 2511.10289 • Published Nov 13, 2025 • 18
view article Article Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines +2 18 days ago • 43