Provides a NumPy/SciPy-compatible GPU array library for Python, enabling existing NumPy/SciPy numerical code to run on NVIDIA CUDA and AMD ROCm with minimal changes. Exposes low-level CUDA features (RawKernels, Streams) and offers prebuilt binaries for multiple CUDA/ROCm versions.
Study core machine-learning methods through compact NumPy implementations, from regression and clustering to neural networks, generative models, and deep Q-learning. The code favors clarity over production performance.
Provides composable function transformations for Python+NumPy—automatic differentiation, JIT compilation, and vectorization—while using XLA to run and scale numerical programs on GPUs/TPUs for ML and scientific computing.
Provides humanoid character meshes with skeleton hierarchies and skinning weights for training and evaluating auto-rigging, skeleton generation, and skinning prediction. It combines multiple source subsets and is restricted to academic research use.
Turns English text into speech, with normalization for natural readings of numbers, dates, prices, and codes. The 40.6 MB model runs locally on a CPU with NumPy and includes Juno and Mira voices.