1 Repo
Awesome GitHub RepositoriesUnsupervised Recognition
Speech recognition systems trained without paired audio-transcript data, typically using self-supervised learning.
Distinct from Speech Recognition: Specifically targets recognition trained without ground-truth transcripts, unlike standard supervised speech recognition.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Unsupervised Recognition. Refine with filters or upvote what's useful.
Awesome Unsupervised Recognition GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- espnet/espnet
espnet/espnet
9,861Auf GitHub ansehenESPnet is a comprehensive speech processing toolkit and PyTorch-based trainer designed for building end-to-end speech recognition, synthesis, and translation models. It provides a structured framework for developing automatic speech recognition systems using transducer and encoder-decoder architectures, alongside engines for text-to-speech synthesis and speech translation pipelines. The project distinguishes itself through a recipe-based workflow execution system that ensures experimental reproducibility by running standardized sequences of scripts for data preparation and model training. It
Implements recognition systems that can be trained without paired transcripts using self-supervised models and decoding graphs.
Python
