ConDigSumCode for EMNLP 2021 paper "Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization"
Stars: ✭ 62 (+37.78%)
CLMROfficial PyTorch implementation of Contrastive Learning of Musical Representations
Stars: ✭ 216 (+380%)
WavegradImplementation of Google Brain's WaveGrad high-fidelity vocoder (paper: https://arxiv.org/pdf/2009.00713.pdf). First implementation on GitHub.
Stars: ✭ 245 (+444.44%)
CCLPyTorch Implementation on Paper [CVPR2021]Distilling Audio-Visual Knowledge by Compositional Contrastive Learning
Stars: ✭ 76 (+68.89%)
KerasdeepspeechA Keras CTC implementation of Baidu's DeepSpeech for model experimentation
Stars: ✭ 245 (+444.44%)
kaldi ag trainingDocker image and scripts for training finetuned or completely personal Kaldi speech models. Particularly for use with kaldi-active-grammar.
Stars: ✭ 14 (-68.89%)
Lhotse Stars: ✭ 236 (+424.44%)
awesome-efficient-gnnCode and resources on scalable and efficient Graph Neural Networks
Stars: ✭ 498 (+1006.67%)
SetkTools for Speech Enhancement integrated with Kaldi
Stars: ✭ 227 (+404.44%)
ViCC[WACV'22] Code repository for the paper "Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting", https://arxiv.org/abs/2106.10137.
Stars: ✭ 33 (-26.67%)
VoluteRaspberry Pi + Nodejs = Speech Robot
Stars: ✭ 224 (+397.78%)
NBSSThe official repo of "Multi-channel Narrow-band Deep Speech Separation with Full-band Permutation Invariant Training", "Multichannel Speech Separation with Narrow-band Conformer" and "NBC2: Multichannel Speech Separation with Revised Narrow-band Conformer".
Stars: ✭ 77 (+71.11%)
capeContinuous Augmented Positional Embeddings (CAPE) implementation for PyTorch
Stars: ✭ 29 (-35.56%)
TimitThe DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus.
Stars: ✭ 202 (+348.89%)
LingvoLingvo
Stars: ✭ 2,361 (+5146.67%)
Revisiting-Contrastive-SSLRevisiting Contrastive Methods for Unsupervised Learning of Visual Representations. [NeurIPS 2021]
Stars: ✭ 81 (+80%)
day2nightImage2Image Translation Research
Stars: ✭ 46 (+2.22%)
Vq Vae SpeechPyTorch implementation of VQ-VAE + WaveNet by [Chorowski et al., 2019] and VQ-VAE on speech signals by [van den Oord et al., 2017]
Stars: ✭ 187 (+315.56%)
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 (-4.44%)
object-aware-contrastiveObject-aware Contrastive Learning for Debiased Scene Representation (NeurIPS 2021)
Stars: ✭ 44 (-2.22%)
Pytorch Kaldipytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
Stars: ✭ 2,097 (+4560%)
UPITA fastai/PyTorch package for unpaired image-to-image translation.
Stars: ✭ 94 (+108.89%)
Tts Papers🐸 collection of TTS papers
Stars: ✭ 160 (+255.56%)
txt2speechConvert text to speech using Google Translate API
Stars: ✭ 38 (-15.56%)
KeenASR-Android-PoCA proof-of-concept app using KeenASR SDK on Android. WE ARE HIRING: https://keenresearch.com/careers.html
Stars: ✭ 21 (-53.33%)
WavegradA fast, high-quality neural vocoder.
Stars: ✭ 138 (+206.67%)
CLSAofficial implemntation for "Contrastive Learning with Stronger Augmentations"
Stars: ✭ 48 (+6.67%)
AllosaurusAllosaurus is a pretrained universal phone recognizer for more than 2000 languages
Stars: ✭ 135 (+200%)
MediumVCAny-to-any voice conversion using synthetic specific-speaker speeches as intermedium features
Stars: ✭ 46 (+2.22%)
Avpian open source voice command macro software
Stars: ✭ 130 (+188.89%)
Asr audio data linksA list of publically available audio data that anyone can download for ASR or other speech activities
Stars: ✭ 128 (+184.44%)
gans-2.0Generative Adversarial Networks in TensorFlow 2.0
Stars: ✭ 76 (+68.89%)
Kaldikaldi-asr/kaldi is the official location of the Kaldi project.
Stars: ✭ 11,151 (+24680%)
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 (+28.89%)
Code Switching PapersA curated list of research papers and resources on code-switching
Stars: ✭ 122 (+171.11%)
GeDMLGeneralized Deep Metric Learning.
Stars: ✭ 30 (-33.33%)
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 (-44.44%)
HolobotHoloBot is a reusable 3D interface that allows HoloLens & VR users to interact with any bot using Mixed Reality & Speech.
Stars: ✭ 114 (+153.33%)
lidboxEnd-to-end spoken language identification out of the box.
Stars: ✭ 39 (-13.33%)
StyleSpeechOfficial implementation of Meta-StyleSpeech and StyleSpeech
Stars: ✭ 161 (+257.78%)
GttsPython library and CLI tool to interface with Google Translate's text-to-speech API
Stars: ✭ 1,303 (+2795.56%)
idear🎙️ Handsfree Audio Development Interface
Stars: ✭ 84 (+86.67%)
COCO-LM[NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
Stars: ✭ 109 (+142.22%)
SingleVCAny-to-one voice conversion using the data augment strategy: pitch shifted and duration remained.
Stars: ✭ 25 (-44.44%)