HandwritingrecognitionsystemHandwriting Recognition System based on a deep Convolutional Recurrent Neural Network architecture
Stars: ✭ 262 (-87.43%)
Comprehensive-Tacotron2PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supports both single-, multi-speaker TTS and several techniques to enforce the robustness and efficiency of the model.
Stars: ✭ 22 (-98.94%)
ParakeetPAddle PARAllel text-to-speech toolKIT (supporting WaveFlow, WaveNet, Transformer TTS and Tacotron2)
Stars: ✭ 279 (-86.62%)
edittsOfficial implementation of EdiTTS: Score-based Editing for Controllable Text-to-Speech
Stars: ✭ 74 (-96.45%)
Seq2seq chatbot基于seq2seq模型的简单对话系统的tf实现,具有embedding、attention、beam_search等功能,数据集是Cornell Movie Dialogs
Stars: ✭ 308 (-85.23%)
Hifi GanHiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
Stars: ✭ 325 (-84.41%)
Seq2seq SummarizerPointer-generator reinforced seq2seq summarization in PyTorch
Stars: ✭ 306 (-85.32%)
Numpy neural network仅使用numpy从头开始实现神经网络,包括反向传播公式推导过程; numpy构建全连接层、卷积层、池化层、Flatten层;以及图像分类案例及精调网络案例等,持续更新中... ...
Stars: ✭ 339 (-83.74%)
Libfaceidlibfaceid is a research framework for prototyping of face recognition solutions. It seamlessly integrates multiple detection, recognition and liveness models w/ speech synthesis and speech recognition.
Stars: ✭ 354 (-83.02%)
leon🧠 Leon is your open-source personal assistant.
Stars: ✭ 8,560 (+310.55%)
Cortex M KwsCortex M KWS example with Tengine Lite.
Stars: ✭ 45 (-97.84%)
Keras SincnetKeras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)
Stars: ✭ 47 (-97.75%)
Zamia SpeechOpen tools and data for cloudless automatic speech recognition
Stars: ✭ 374 (-82.06%)
Java Speech ApiThe J.A.R.V.I.S. Speech API is designed to be simple and efficient, using the speech engines created by Google to provide functionality for parts of the API. Essentially, it is an API written in Java, including a recognizer, synthesizer, and a microphone capture utility. The project uses Google services for the synthesizer and recognizer. While this requires an Internet connection, it provides a complete, modern, and fully functional speech API in Java.
Stars: ✭ 490 (-76.5%)
Transformer TtsA Pytorch Implementation of "Neural Speech Synthesis with Transformer Network"
Stars: ✭ 418 (-79.95%)
Char rnn lm zhlanguage model in Chinese,基于Pytorch官方文档实现
Stars: ✭ 57 (-97.27%)
EspnetEnd-to-End Speech Processing Toolkit
Stars: ✭ 4,533 (+117.41%)
Multi Class Text Classification Cnn RnnClassify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.
Stars: ✭ 570 (-72.66%)
Awesome Bert NlpA curated list of NLP resources focused on BERT, attention mechanism, Transformer networks, and transfer learning.
Stars: ✭ 567 (-72.81%)
MaryttsMARY TTS -- an open-source, multilingual text-to-speech synthesis system written in pure java
Stars: ✭ 1,699 (-18.51%)
SincnetSincNet is a neural architecture for efficiently processing raw audio samples.
Stars: ✭ 764 (-63.36%)
PykaldiA Python wrapper for Kaldi
Stars: ✭ 756 (-63.74%)
Seq2seq chatbot new基于seq2seq模型的简单对话系统的tf实现,具有embedding、attention、beam_search等功能,数据集是Cornell Movie Dialogs
Stars: ✭ 144 (-93.09%)
Fre-GAN-pytorchFre-GAN: Adversarial Frequency-consistent Audio Synthesis
Stars: ✭ 73 (-96.5%)
Rnn Theano使用Theano实现的一些RNN代码,包括最基本的RNN,LSTM,以及部分Attention模型,如论文MLSTM等
Stars: ✭ 31 (-98.51%)
LightspeechLightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search
Stars: ✭ 31 (-98.51%)
Boilerplate Dynet Rnn LmBoilerplate code for quickly getting set up to run language modeling experiments
Stars: ✭ 37 (-98.23%)
Jsut LabHTS-style full-context labels for JSUT v1.1
Stars: ✭ 28 (-98.66%)
Kaldikaldi-asr/kaldi is the official location of the Kaldi project.
Stars: ✭ 11,151 (+434.82%)
Dialectid e2eEnd to End Dialect Identification using Convolutional Neural Network
Stars: ✭ 40 (-98.08%)
Py NltoolsA collection of basic python modules for spoken natural language processing
Stars: ✭ 46 (-97.79%)
AilearningAiLearning: 机器学习 - MachineLearning - ML、深度学习 - DeepLearning - DL、自然语言处理 NLP
Stars: ✭ 32,316 (+1449.93%)
Cs224n Gpu That TalksAttention, I'm Trying to Speak: End-to-end speech synthesis (CS224n '18)
Stars: ✭ 52 (-97.51%)
Mxnet Seq2seqSequence to sequence learning with MXNET
Stars: ✭ 51 (-97.55%)
DeepseqslamThe Official Deep Learning Framework for Route-based Place Recognition
Stars: ✭ 49 (-97.65%)
Speech aiSimple speech linguistic AI with Python
Stars: ✭ 66 (-96.83%)
Nlp overviewOverview of Modern Deep Learning Techniques Applied to Natural Language Processing
Stars: ✭ 1,104 (-47.05%)
Patterspeech-to-text in pytorch
Stars: ✭ 71 (-96.59%)
SleepeegnetSleepEEGNet: Automated Sleep Stage Scoring with Sequence to Sequence Deep Learning Approach
Stars: ✭ 89 (-95.73%)
Cross vcCross-lingual Voice Conversion
Stars: ✭ 91 (-95.64%)
Attention OcrA Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.
Stars: ✭ 844 (-59.52%)
Parrots Automatic Speech Recognition(ASR), Text-To-Speech(TTS) engine for Chinese.
Stars: ✭ 48 (-97.7%)
Cnn vocoderA fast cnn-based vocoder
Stars: ✭ 74 (-96.45%)
Tensorflowtts😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
Stars: ✭ 2,382 (+14.24%)
CodesearchnetDatasets, tools, and benchmarks for representation learning of code.
Stars: ✭ 1,378 (-33.91%)
CaptcharecognitionEnd-to-end variable length Captcha recognition using CNN+RNN+Attention/CTC (pytorch implementation). 端到端的不定长验证码识别
Stars: ✭ 97 (-95.35%)
Tacotron PytorchA Pytorch Implementation of Tacotron: End-to-end Text-to-speech Deep-Learning Model
Stars: ✭ 104 (-95.01%)
AdnetAttention-guided CNN for image denoising(Neural Networks,2020)
Stars: ✭ 135 (-93.53%)
WavernnWaveRNN Vocoder + TTS
Stars: ✭ 1,636 (-21.53%)
CrystalCrystal - C++ implementation of a unified framework for multilingual TTS synthesis engine with SSML specification as interface.
Stars: ✭ 108 (-94.82%)