warp-ctc
Speech recognition library
PyTorch bindings for the Warp-CTC loss function used in speech recognition.
Pytorch Bindings for warp-ctc
757 stars
17 watching
271 forks
Language: Cuda
last commit: over 1 year ago Related projects:
| Repository | Description | Stars |
|---|---|---|
| seannaren/deepspeech.pytorch | A deep learning-based speech recognition system built on top of PyTorch Lightning. | 2,104 |
 ryanleary/ctcdecode | A PyTorch implementation of the Connectionist Temporal Classification (CTC) decoding algorithm for speech recognition and text analysis tasks. | 42 |
| seannaren/deepspeech.torch | A speech recognition system based on the DeepSpeech2 architecture | 259 |
 torch/cutorch | Provides a CUDA backend for the PyTorch deep learning framework | 336 |
 yerevann/warp | An approach to transfer learning for NLP tasks using adversarial reprogramming and word-level task-specific embeddings. | 83 |
 skyduy/cnn_keras | An implementation of a Convolutional Neural Network using Keras for CAPTCHA recognition and classification | 288 |
 huguyuehuhu/hcn-pytorch | Replication of a PyTorch model for action recognition and detection from skeleton data | 219 |
 openseg-group/openseg.pytorch | Provides a PyTorch implementation of several computer vision tasks including object detection, segmentation and parsing. | 1,190 |
 longcw/roialign.pytorch | Implementation of RoIAlign and crop_and_resize functions for PyTorch | 554 |
 randl/shufflenetv2-pytorch | An implementation of a lightweight convolutional neural network architecture for mobile devices | 191 |
 rusty1s/pytorch_cluster | A PyTorch extension library providing optimized graph cluster algorithms | 824 |
 yunlongdong/fcn-pytorch | A PyTorch implementation of FCN for semantic segmentation with an easy-to-use interface and pre-trained models. | 160 |
 shawn1993/cnn-text-classification-pytorch | An implementation of Kim's Convolutional Neural Networks for Sentence Classification in PyTorch | 1,020 |
 soobinseo/tacotron-pytorch | A PyTorch implementation of an end-to-end text-to-speech synthesis model. | 206 |
 kaiyangzhou/dassl.pytorch | A PyTorch toolbox for supporting research and development of domain adaptation, generalization, and semi-supervised learning methods in computer vision. | 1,217 |