kevobt/speech-to-text

Speech recognition framework using keras

21
/ 100
Experimental

This framework helps you build your own custom speech recognition system. You provide audio recordings paired with their exact text transcripts, and it trains a neural network model. The output is a trained model that can convert new audio files into text. This is designed for researchers or developers who need to create specialized speech-to-text capabilities for specific domains or languages.

No commits in the last 6 months.

Use this if you need to train a speech recognition model on your unique dataset of audio and text, perhaps for a specialized vocabulary or language not well-covered by existing off-the-shelf solutions.

Not ideal if you simply need to transcribe audio using a pre-trained, general-purpose speech-to-text service without needing to build or customize the underlying model.

speech-recognition-training custom-transcription audio-processing machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

Python

License

GPL-3.0

Last pushed

May 18, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/kevobt/speech-to-text"

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