alexcannan
Follow
Stars
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
DSPy: The framework for programming—not prompting—language models
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
Amundsen is a metadata driven application for improving the productivity of data analysts, data scientists and engineers when interacting with data.
Fast job queuing and RPC in python with asyncio and redis.
Social reading and reviewing, decentralized with ActivityPub
Code for the paper "Improved Techniques for Training GANs"
Interact, analyze and structure massive text, image, embedding, audio and video datasets
🏔️ Mountaineer is a batteries-included webapp framework for Python.
Speech Enhancement Generative Adversarial Network in TensorFlow
CNN-based audio segmentation toolkit. Allows to detect speech, music, noise and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.
A bidirectional recurrent neural network model with attention mechanism for restoring missing punctuation in unsegmented text
Experiments with applying Fourier transofrms to various plane-filling curves and patterns
Code for prefix beam search tutorial by @labodk
An easy-to-use Python module that helps you to extract the BERT embeddings for a large text dataset (Bengali/English) efficiently.
Noisy Quantum Gates model for simulating the noise of quantum devices.
GPT-2 Metadata Pretraining Towards Instruction Finetuning for Ukrainian
Scripts to simplify data prepping for Mozilla DeepSpeech.
Fast word segmentation with a focus on splitting #hashtags