Listen-Attend-Spell and Listen-Attend-Spell-v2
These are competing implementations of the same LAS (Listen, Attend and Spell) architecture for ASR, so users would select one based on code quality, documentation, and feature completeness rather than use them together.
About Listen-Attend-Spell
kaituoxu/Listen-Attend-Spell
A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.
The implementation uses a encoder-decoder architecture with attention mechanisms, where the listener (encoder) processes acoustic features via bidirectional LSTMs and the speller (decoder) generates character sequences autoregressively. It integrates with Kaldi for acoustic feature extraction and includes built-in support for Visdom visualization of training metrics. The framework includes a complete pipeline for data preparation, training, and decoding, with example scripts targeting the AISHELL Mandarin speech corpus.
About Listen-Attend-Spell-v2
foamliu/Listen-Attend-Spell-v2
PyTorch implementation of Listen Attend and Spell Automatic Speech Recognition (ASR).
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work