subho406/TF-Speech-Recognition-Challenge-Solution

Source code of the model used in Tensorflow Speech Recognition Challenge (https://www.kaggle.com/c/tensorflow-speech-recognition-challenge). The solution ranked in top 5% in private leaderboard.

44
/ 100
Emerging

This project provides a pre-built solution for recognizing simple spoken commands from audio recordings. You feed it audio files containing single words, and it tells you which command was spoken. This is useful for anyone developing or prototyping systems that need to understand basic voice commands, such as smart home devices, accessibility tools, or interactive voice response systems.

No commits in the last 6 months.

Use this if you need a high-performing baseline or a direct solution for classifying single-word audio commands like 'yes', 'no', 'up', or 'down'.

Not ideal if you need to recognize continuous speech, complex sentences, or commands not present in the Speech Commands Dataset.

voice-control audio-classification embedded-systems assistive-technology
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

58

Forks

28

Language

Jupyter Notebook

License

GPL-3.0

Last pushed

Mar 30, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/subho406/TF-Speech-Recognition-Challenge-Solution"

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