Caffe is a deep learning framework for computer vision, with configurable neural networks, pretrained models and CPU/GPU execution.
Read more
Caffe is a deep learning framework for computer vision, with configurable neural networks, pretrained models and CPU/GPU execution.
Read more
Keras is a multi-backend neural network API for TensorFlow, JAX and PyTorch, with model building, training, evaluation and export.
Read more
PyTorch is a deep learning framework with dynamic tensors, automatic differentiation, model compilation and distributed training.
Read more
TensorFlow is a machine learning framework with automatic differentiation, model training, distributed execution and deployment tools.
Read more
deepspeech.pytorch trains and evaluates DeepSpeech2 speech recognition models with CTC decoding, data augmentation and multi-GPU support.
Read more
ESPnet supports speech recognition, synthesis, translation, enhancement and diarization with reproducible experiments and pretrained models.
Read more
Kaldi provides speech recognition research tools with finite-state decoding, acoustic modelling, neural networks and reproducible recipes.
Read more
SpeechBrain supports speech recognition, speaker analysis, speech enhancement and speech synthesis with pretrained models and recipes.
Read more
Flashlight is a fast, flexible machine learning library written entirely in C++. It provides apps for research across multiple domains.
Read more
flair provides neural NLP models, embeddings and training tools for named entity recognition, sequence tagging and text classification.
Read more
PyTorch-NLP supplies text encoders, word vectors, dataset readers, neural network modules, samplers and evaluation metrics.
Read more
Transformers provides pretrained models and tools for text classification, generation, translation, summarisation and language analysis.
Read more
NLP Architect provides research models and utilities for natural language understanding, entity recognition and intent extraction.
Read more
AllenNLP is a research framework for language understanding with dataset readers, modelling components and experiment configuration.
Read more
GluonNLP provides neural NLP research utilities, pretrained models, data preprocessing and text model training with MXNet.
Read more
LibreTranslate is a machine translation API which is entirely self-hosted. This software lets you use open source machine translation in your projects.
Read more
Argos Translate is state of the art neural machine translation software. It’s written in Python and published under an open source license.
Read more
Audiocraft is Python-based software which provides the code and models for MusicGen, a simple and controllable model for music generation.
Read more
Spleeter is a source separation library with pre-trained models written in Python. It’s free and open source software.
Read more
CodeFormer is software which offers blind face restoration. This is freeware.
Read more