creafz/kaggle-speech-recognition

Solution for TensorFlow Speech Recognition Challenge on Kaggle (125th place, top 10%)

33
/ 100
Emerging

This project helps classify short, one-second spoken commands into predefined categories like "yes," "no," or "stop." It takes audio files of spoken words and outputs a label for each word, determining what was said. This is useful for engineers developing voice control features or conversational AI systems.

No commits in the last 6 months.

Use this if you need a baseline system for accurately identifying specific spoken commands from short audio clips.

Not ideal if you need to transcribe long-form speech, recognize a very large vocabulary, or work with languages other than English.

voice-user-interface speech-recognition audio-classification command-and-control conversational-ai
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

11

Forks

2

Language

Python

License

MIT

Last pushed

Jan 21, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/creafz/kaggle-speech-recognition"

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