> ML_LIBRARIES_CATALOG_v1.0
Qualified ML Libraries
Every library is independently qualified with primary citations, supported version ranges, hardware accelerator separation, and real-world failure patterns.
EconML
Microsoft Research / PyWhy
Microsoft Research and PyWhy toolkit for estimating Heterogeneous Treatment Effects via Double Machine Learning.
CausalML
Uber Open Source
Uber's production uplift modeling and causal machine learning library for targeted campaigns.
lifelines
Cameron Davidson-Pilon
Complete survival analysis and time-to-event modeling library for Python.
PyTorch Geometric (PyG)
PyG Team / Stanford University / Kumo AI
Premier Graph Neural Network library built on PyTorch for irregular relational structures.
Deep Graph Library (DGL)
DMLC / AWS / NYU
Enterprise graph deep learning framework optimized for multi-node billion-edge distributed training.
NetworkX
NetworkX Developers / NumFOCUS
Universal Python library for the creation, manipulation, and algorithmic study of complex networks.
implicit
Ben Frederickson
Fast, GPU-accelerated collaborative filtering for implicit feedback datasets in Python.
Surprise (scikit-surprise)
Nicolas Hug / scikit-surprise developers
scikit-learn compatible Python library for explicit rating recommender systems and matrix factorization.
RecBole
RUCAIBox / Renmin University of China
Unified deep learning recommender library implementing over 80 neural algorithms in PyTorch.
TensorFlow Recommenders (TFRS)
Google / TensorFlow Team
Google's open-source framework for building Two-Tower retrieval and ranking models in TensorFlow.
NVIDIA Merlin
NVIDIA Corporation
NVIDIA's end-to-end GPU-accelerated platform for building multi-terabyte recommender systems.
librosa
Brian McFee / librosa development team
Foundational Python library for music information retrieval and audio feature extraction.
torchaudio
PyTorch Foundation / Meta
Official PyTorch library for GPU-accelerated audio transforms and deep speech models.
SpeechBrain
SpeechBrain Consortium / Inria / Mila
All-in-one conversational speech toolkit built on PyTorch for ASR, speaker verification, and speech synthesis.
NVIDIA NeMo
NVIDIA Corporation
NVIDIA's enterprise framework for training and deploying conversational AI and speech foundation models.
OpenAI Whisper
OpenAI
OpenAI's foundational speech recognition and multilingual translation transformer model.
faster-whisper
SYSTRAN
High-speed Whisper speech recognition engine delivering up to 4x throughput using CTranslate2.
pyannote.audio
Hervé Bredin / CNRS / pyannote
State-of-the-art neural speaker diarization toolkit for identifying "who spoke when" in audio.