creafz/kaggle-speech-recognition
Solution for TensorFlow Speech Recognition Challenge on Kaggle (125th place, top 10%)
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.
Stars
11
Forks
2
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
julius-speech/julius
Open-Source Large Vocabulary Continuous Speech Recognition Engine
rolczynski/Automatic-Speech-Recognition
🎧 Automatic Speech Recognition: DeepSpeech & Seq2Seq (TensorFlow)
tabahi/formantfeatures
Extract frequency, power, width and dissonance of formants from wav files
libdriver/ld3320
LD3320 full-featured driver library for general-purpose MCU and Linux.
awsaf49/audio_classification_models
Tensorflow Audio Classification Models