kaituoxu/Speech-Transformer

A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.

43
/ 100
Emerging

This tool helps developers working with Mandarin Chinese speech convert audio recordings directly into written text using an advanced neural network. It takes acoustic features derived from speech audio as input and outputs the corresponding character sequence. This is primarily for machine learning engineers or researchers focused on developing and evaluating automatic speech recognition (ASR) systems.

809 stars. No commits in the last 6 months.

Use this if you are a developer researching or building an end-to-end Automatic Speech Recognition (ASR) system for Mandarin Chinese and want to use a Transformer-based architecture.

Not ideal if you are looking for a ready-to-use application to transcribe Mandarin Chinese audio without needing to dive into machine learning model training and development.

automatic-speech-recognition mandarin-chinese natural-language-processing deep-learning-research audio-transcription
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 25 / 25

How are scores calculated?

Stars

809

Forks

196

Language

Python

License

Last pushed

Apr 06, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/kaituoxu/Speech-Transformer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.