Explore Projects
Discover 17 open source projects
Showing 1-17 of 17 projects
speechbrain/speechbrain
A PyTorch-based toolkit for speech processing, including ASR, speaker recognition, and speech enhancement.
pyannote/pyannote-audio
A neural network library for speaker diarization, including speech activity detection, speaker change detection, and speaker embedding.
snakers4/silero-vad
Silero VAD is a pre-trained enterprise-grade Voice Activity Detector library for Python.
pliang279/awesome-multimodal-ml
A comprehensive reading list for research topics in multimodal machine learning.
microsoft/torchscale
Foundation Architecture for (M)LLMs, a powerful toolkit for building large language models.
linto-ai/whisper-timestamped
An open-source library for multilingual automatic speech recognition with word-level timestamps and confidence.
r9y9/wavenet_vocoder
A high-quality open-source PyTorch implementation of the WaveNet vocoder, a neural network for speech synthesis.
resemble-ai/resemble-enhance
An AI-powered speech denoising and enhancement library for improving audio quality.
DigitalPhonetics/IMS-Toucan
A fast and controllable text-to-speech library supporting over 7000 languages using deep learning and PyTorch.
TEN-framework/ten-vad
A lightweight, high-performance voice activity detector (VAD) library for conversational AI and real-time speech processing.
r9y9/deepvoice3_pytorch
A PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models.
wq2012/awesome-diarization
A curated list of resources for speaker diarization, a speech processing task to identify who spoke when.
coqui-ai/open-speech-corpora
A collection of open-source speech corpora for building speech recognition, synthesis, and other audio applications.
haoheliu/voicefixer
A Python library for speech restoration, including tasks like declipping, denoising, and dereverberation.
ictnlp/StreamSpeech
An all-in-one model for offline and simultaneous speech recognition, translation, and synthesis.
mravanelli/SincNet
SincNet is a neural architecture for efficiently processing raw audio samples for speech and audio processing tasks.
midas-research/audino
Open-source audio annotation tool for machine learning and speech processing datasets.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.