LaTeX-OCRpix2tex: Using a ViT to convert images of equations into LaTeX code.
Stars: ✭ 1,566 (+5300%)
OpenasrA pytorch based end2end speech recognition system.
Stars: ✭ 69 (+137.93%)
speech-transformerTransformer implementation speciaized in speech recognition tasks using Pytorch.
Stars: ✭ 40 (+37.93%)
Nlp Experiments In PytorchPyTorch repository for text categorization and NER experiments in Turkish and English.
Stars: ✭ 35 (+20.69%)
Neural spEnd-to-end ASR/LM implementation with PyTorch
Stars: ✭ 408 (+1306.9%)
towheeTowhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
Stars: ✭ 821 (+2731.03%)
AdaSpeechAdaSpeech: Adaptive Text to Speech for Custom Voice
Stars: ✭ 108 (+272.41%)
Zero-Shot-TTSUnofficial Implementation of Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration
Stars: ✭ 33 (+13.79%)
FNet-pytorchUnofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms
Stars: ✭ 204 (+603.45%)
Aeneasaeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)
Stars: ✭ 1,942 (+6596.55%)
vietnamese-robertaA Robustly Optimized BERT Pretraining Approach for Vietnamese
Stars: ✭ 22 (-24.14%)
anycontrolVoice control for your websites and applications
Stars: ✭ 53 (+82.76%)
densecapDense video captioning in PyTorch
Stars: ✭ 37 (+27.59%)
clifsContrastive Language-Image Forensic Search allows free text searching through videos using OpenAI's machine learning model CLIP
Stars: ✭ 271 (+834.48%)
pytorch-pcenPyTorch reimplementation of per-channel energy normalization for audio.
Stars: ✭ 80 (+175.86%)
jominiLow level, performance oriented parser for save and game files from EU4, CK3, HOI4, Vic3, Imperator, and other PDS titles.
Stars: ✭ 40 (+37.93%)
sb-nmtCode for Synchronous Bidirectional Neural Machine Translation (SB-NMT)
Stars: ✭ 66 (+127.59%)
Transformers-RLAn easy PyTorch implementation of "Stabilizing Transformers for Reinforcement Learning"
Stars: ✭ 107 (+268.97%)
libaiLiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training
Stars: ✭ 284 (+879.31%)
ru-dalleGenerate images from texts. In Russian
Stars: ✭ 1,606 (+5437.93%)
readthatRead Text Data
Stars: ✭ 27 (-6.9%)
awesome-transformer-searchA curated list of awesome resources combining Transformers with Neural Architecture Search
Stars: ✭ 194 (+568.97%)
vue-swimlaneA Text Swimlane plugin for Vue.js
Stars: ✭ 71 (+144.83%)
textalyzerAnalyze key metrics like number of words, readability, complexity, etc. of any kind of text
Stars: ✭ 50 (+72.41%)
php-serializerSerialize PHP variables, including objects, in any format. Support to unserialize it too.
Stars: ✭ 47 (+62.07%)
TF-Speech-Recognition-Challenge-SolutionSource code of the model used in Tensorflow Speech Recognition Challenge (https://www.kaggle.com/c/tensorflow-speech-recognition-challenge). The solution ranked in top 5% in private leaderboard.
Stars: ✭ 58 (+100%)
ventib📈 Ventib records your voice, transcribes it in realtime, and performs speech pattern analysis to give you objective statistics about how you speak.
Stars: ✭ 43 (+48.28%)
SegSwap(CVPRW 2022) Learning Co-segmentation by Segment Swapping for Retrieval and Discovery
Stars: ✭ 46 (+58.62%)
BMTSource code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)
Stars: ✭ 192 (+562.07%)
bytekitJava 字节操作的工具库(不是字节码的工具库)
Stars: ✭ 40 (+37.93%)
Multimodal-Gesture-Recognition-with-LSTMs-and-CTCAn end-to-end system that performs temporal recognition of gesture sequences using speech and skeletal input. The model combines three networks with a CTC output layer that recognises gestures from continuous stream.
Stars: ✭ 25 (-13.79%)
ASR-Audio-Data-LinksA list of publically available audio data that anyone can download for ASR or other speech activities
Stars: ✭ 179 (+517.24%)
IMS-ToucanText-to-Speech Toolkit of the Speech and Language Technologies Group at the University of Stuttgart. Objectives of the development are simplicity, modularity, controllability and multilinguality.
Stars: ✭ 295 (+917.24%)
t5-japaneseCodes to pre-train Japanese T5 models
Stars: ✭ 39 (+34.48%)
seq2seq-pytorchSequence to Sequence Models in PyTorch
Stars: ✭ 41 (+41.38%)
transformerBuild English-Vietnamese machine translation with ProtonX Transformer. :D
Stars: ✭ 41 (+41.38%)
wav2vec2-liveA live speech recognition using Facebooks wav2vec 2.0 model.
Stars: ✭ 205 (+606.9%)
VQMIVCOfficial implementation of VQMIVC: One-shot (any-to-any) Voice Conversion @ Interspeech 2021 + Online playing demo!
Stars: ✭ 278 (+858.62%)
TextBoxesTextBoxes: A Fast Text Detector with a Single Deep Neural Network
Stars: ✭ 625 (+2055.17%)
fastT5⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
Stars: ✭ 421 (+1351.72%)
txt2speechConvert text to speech using Google Translate API
Stars: ✭ 38 (+31.03%)
idear🎙️ Handsfree Audio Development Interface
Stars: ✭ 84 (+189.66%)
SilentServerSilent is very lightweight, high quality - low latency voice chat for gaming. The server runs on Windows and Linux.
Stars: ✭ 52 (+79.31%)
react-bones💀 Dead simple content loading components for React and React-Native. 💀
Stars: ✭ 42 (+44.83%)
nested-transformerNested Hierarchical Transformer https://arxiv.org/pdf/2105.12723.pdf
Stars: ✭ 174 (+500%)
Cross-lingual-SummarizationZero-Shot Cross-Lingual Abstractive Sentence Summarization through Teaching Generation and Attention
Stars: ✭ 28 (-3.45%)
ViTs-vs-CNNs[NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)
Stars: ✭ 145 (+400%)
markdownmarkdown tools, libraries & scripts
Stars: ✭ 52 (+79.31%)
SSE-PTCodes and Datasets for paper RecSys'20 "SSE-PT: Sequential Recommendation Via Personalized Transformer" and NurIPS'19 "Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers"
Stars: ✭ 103 (+255.17%)
VT-UNet[MICCAI2022] This is an official PyTorch implementation for A Robust Volumetric Transformer for Accurate 3D Tumor Segmentation
Stars: ✭ 151 (+420.69%)
MailDemonSmtp server for mass emailing, managing email lists and more. Built on .NET Core. Linux, MAC and Windows compatible.
Stars: ✭ 113 (+289.66%)