huschen/kaggle_speech_recognition

Conv-LSTM-CTC speech recognition network (end-to-end), written in TensorFlow.

44
/ 100
Emerging

This project helps you automatically detect simple spoken commands, like "yes" or "no", from audio recordings. It takes sound wave files as input and outputs the recognized command as text. This tool is designed for anyone needing to build or evaluate a system that understands specific voice commands.

No commits in the last 6 months.

Use this if you need to build a system that can reliably identify a limited set of spoken keywords from audio data.

Not ideal if you need to transcribe open-ended speech or handle a very large, diverse vocabulary, as it's optimized for discrete command recognition.

speech-recognition voice-commands audio-processing natural-language-processing human-computer-interaction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

72

Forks

20

Language

Python

License

MIT

Last pushed

Mar 21, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/huschen/kaggle_speech_recognition"

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