Listen-Attend-Spell-v2 and Listen-Attend-Spell
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-v2
foamliu/Listen-Attend-Spell-v2
PyTorch implementation of Listen Attend and Spell Automatic Speech Recognition (ASR).
This project offers a foundational system for converting spoken Chinese Mandarin into written text. You provide audio recordings in Mandarin, and it produces a transcript of what was said. Researchers and developers working on speech recognition systems for Mandarin would find this useful for building or experimenting with new models.
About Listen-Attend-Spell
kaituoxu/Listen-Attend-Spell
A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.
This project helps machine learning engineers or researchers build custom automatic speech recognition (ASR) systems. It takes raw acoustic features from audio and converts them directly into sequences of characters. The output is a trained model capable of transcribing spoken language.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work