bminixhofer / Nnsplit
Licence: mit
Semantic text segmentation. For sentence boundary detection, compound splitting and more.
Stars: ✭ 141
Programming Languages
javascript
184084 projects - #8 most used programming language
python
139335 projects - #7 most used programming language
rust
11053 projects
Projects that are alternatives of or similar to Nnsplit
People Counter Python
Create a smart video application using the Intel Distribution of OpenVINO toolkit. The toolkit uses models and inference to run single-class object detection.
Stars: ✭ 62 (-56.03%)
Mutual labels: pretrained-models
Dimenet
DimeNet and DimeNet++ models, as proposed in "Directional Message Passing for Molecular Graphs" (ICLR 2020) and "Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules" (NeurIPS-W 2020)
Stars: ✭ 106 (-24.82%)
Mutual labels: pretrained-models
Imagenet
Pytorch Imagenet Models Example + Transfer Learning (and fine-tuning)
Stars: ✭ 134 (-4.96%)
Mutual labels: pretrained-models
Dialogue Understanding
This repository contains PyTorch implementation for the baseline models from the paper Utterance-level Dialogue Understanding: An Empirical Study
Stars: ✭ 77 (-45.39%)
Mutual labels: pretrained-models
Covid Twitter Bert
Pretrained BERT model for analysing COVID-19 Twitter data
Stars: ✭ 101 (-28.37%)
Mutual labels: pretrained-models
Mff Pytorch
Motion Fused Frames implementation in PyTorch, codes and pretrained models.
Stars: ✭ 116 (-17.73%)
Mutual labels: pretrained-models
Gpt2 Ml
GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型
Stars: ✭ 1,066 (+656.03%)
Mutual labels: pretrained-models
Diffwave
DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.
Stars: ✭ 139 (-1.42%)
Mutual labels: pretrained-models
Ghostnet
CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.
Stars: ✭ 1,744 (+1136.88%)
Mutual labels: pretrained-models
Electra
中文 预训练 ELECTRA 模型: 基于对抗学习 pretrain Chinese Model
Stars: ✭ 132 (-6.38%)
Mutual labels: pretrained-models
Gen Efficientnet Pytorch
Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS
Stars: ✭ 1,275 (+804.26%)
Mutual labels: pretrained-models
Hbonet
[ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions
Stars: ✭ 94 (-33.33%)
Mutual labels: pretrained-models
Mdm
A TensorFlow implementation of the Mnemonic Descent Method.
Stars: ✭ 120 (-14.89%)
Mutual labels: pretrained-models
Farm
🏡 Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.
Stars: ✭ 1,140 (+708.51%)
Mutual labels: pretrained-models
Breast density classifier
Breast density classification with deep convolutional neural networks
Stars: ✭ 137 (-2.84%)
Mutual labels: pretrained-models
Pytorch Image Models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
Stars: ✭ 15,232 (+10702.84%)
Mutual labels: pretrained-models
Transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Stars: ✭ 55,742 (+39433.33%)
Mutual labels: pretrained-models
Glasses
High-quality Neural Networks for Computer Vision 😎
Stars: ✭ 138 (-2.13%)
Mutual labels: pretrained-models
Pretrained
Pretrained is the most complete and frequently updated list of pretrained top-performing models. Tensorflow, Theano and others. Want to add your model? File an issue, and we will add it.
Stars: ✭ 129 (-8.51%)
Mutual labels: pretrained-models
NNSplit
A tool to split text using a neural network. The main application is sentence boundary detection, but e. g. compound splitting for German is also supported.
Features
- Robust: Not reliant on proper punctuation, spelling and case. See the metrics.
- Small: NNSplit uses a byte-level LSTM, so weights are small (< 4MB) and models can be trained for every unicode encodable language.
- Portable: NNSplit is written in Rust with bindings for Rust, Python, and Javascript (Browser and Node.js). See how to get started in the usage section.
- Fast: Up to 2x faster than Spacy sentencization, see the benchmark.
- Multilingual: NNSplit currently has models for 7 different languages (German, English, French, Norwegian, Swedish, Simplified Chinese, Turkish). Try them in the demo.
Documentation has moved to the NNSplit website: https://bminixhofer.github.io/nnsplit.
License
NNSplit is licensed under the MIT license.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].