LAS_Mandarin_PyTorch and Listen-Attend-Spell

These tools are competitors, as `jackaduma/LAS_Mandarin_PyTorch` appears to be a specialized adaptation of the foundational Listen, Attend and Spell (LAS) framework implemented in `kaituoxu/Listen-Attend-Spell`, specifically targeting Chinese Mandarin with a pretrained model.

LAS_Mandarin_PyTorch
42
Emerging
Listen-Attend-Spell
40
Emerging
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 16/25
Maintenance 0/25
Adoption 10/25
Maturity 8/25
Community 22/25
Stars: 123
Forks: 17
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 207
Forks: 56
Downloads:
Commits (30d): 0
Language: Python
License:
Stale 6m No Package No Dependents
No License Stale 6m No Package No Dependents

About LAS_Mandarin_PyTorch

jackaduma/LAS_Mandarin_PyTorch

Listen, attend and spell Model and a Chinese Mandarin Pretrained model (中文-普通话 ASR模型)

This project provides an established 'Listen, Attend and Spell' model specifically for converting spoken Chinese Mandarin into written text. It takes audio recordings in Mandarin and outputs the corresponding transcribed text. This is designed for researchers or practitioners working on Chinese language processing and speech-to-text applications.

Chinese-Mandarin speech-to-text audio-transcription natural-language-processing linguistics-research

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.

automatic-speech-recognition machine-learning-engineering natural-language-processing deep-learning-research

Scores updated daily from GitHub, PyPI, and npm data. How scores work