TensorFlow Lite
Google's on-device ML inference framework
Episodes
-
#5456: Parakeet vs Whisper: Picking a Phone ASR ModelWhy Whisper loses on Android, why Parakeet v2 beat v3, and how to benchmark speech-to-text without any tooling. -
#120: Silencing the Siren: Real-Time AI Noise ReductionHow do phones remove sirens and crying babies in real time? Explore the neural networks and hardware making crystal-clear audio possible. -
#3: Safetensors or something else: STT inference formats explainedUnpacking ASR weight formats: Safetensors and beyond. Tune in to understand the distinctions.