Pinned Repositories
fvcore
Collection of common code that's shared among different research projects in FAIR computer vision team.
distil-whisper
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
labs
Labs for the EE292D Edge ML class at Stanford
model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
SpecAugmentPyTorch
A Pytorch (support batch and channel) implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Speech_Enhancement_MMSE-STSA
A statistical model-based Speech Enhancement Using MMSE-STSA
distil-whisper
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
silero-models
Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
moonshine
Fast and accurate automatic speech recognition (ASR) for edge devices
guynich's Repositories
guynich/distil-whisper
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
guynich/labs
Labs for the EE292D Edge ML class at Stanford
guynich/model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
guynich/SpecAugmentPyTorch
A Pytorch (support batch and channel) implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
guynich/Speech_Enhancement_MMSE-STSA
A statistical model-based Speech Enhancement Using MMSE-STSA