lalimili6's repositories
allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
asv-subtools
An Open Source Tools for Speaker Recognition
bash-fun
Functional programming in bash
DeepLearningExamples
Deep Learning Examples
gentle
gentle forced aligner
goclassy
An asynchronous concurrent pipeline for classifying Common Crawl based on fastText's pipeline.
iMoCap
dataset for ECCV 2020 "Motion Capture from Internet Videos"
lattice_combination
Lattice combination algorithm to combine inaccurate transcripts with hypothesis lattices
LPCNet
Efficient neural speech synthesis
mcnCrossModalEmotions
Supporting code for "Emotion Recognition in Speech using Cross-Modal Transfer in the Wild"
neural_sp
End-to-end ASR/LM implementation with PyTorch
opendcd
Open Source WFST-based Decoder Toolkit
pysepm
Python implementation of performance metrics in Loizou's Speech Enhancement book
Self-Supervised-Speech-Pretraining-and-Representation-Learning
The S3PRL speech toolkit: self-supervised pre-training and representation learning of Mockingjay, TERA, A-ALBERT, APC, and more to come. With easy-to-use standard downstream evaluation scripts including phone classification, speaker recognition, and ASR. (All in Pytorch!)
ShEMO
Sharif Emotional Speech Database
speechmetrics
A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR
speechsquad
Conversational AI Benchmark.
tacotron
A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
TensorFlowTTS
:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, Korean, Chinese and Easy to adapt for other languages)
vegeta
HTTP load testing tool and library. It's over 9000!
vosk-api
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
watson-voice-bot
Create a Watson Assistant chatbot that uses voice over a web browser.
WavAugment
A library for speech data augmentation in time-domain
WaveRNN
WaveRNN Vocoder + TTS
wer_are_we
Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.