philipperemy/tensorflow-ctc-speech-recognition

Application of Connectionist Temporal Classification (CTC) for Speech Recognition (Tensorflow 1.0 but compatible with 2.0).

48
/ 100
Emerging

This project helps speech technologists and researchers convert spoken audio into written text using a neural network approach. You provide audio files of someone speaking, and it attempts to transcribe those words into a written transcript. It's designed for those exploring or implementing speech recognition systems, particularly with Connectionist Temporal Classification (CTC).

131 stars. No commits in the last 6 months.

Use this if you are a speech recognition researcher or engineer working with English audio data and want to experiment with CTC-based speech-to-text models.

Not ideal if you need an out-of-the-box, production-ready speech recognition system for diverse speakers or languages, or if you are not comfortable with machine learning model training.

speech-to-text audio-transcription natural-language-processing acoustic-modeling voice-technology
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

131

Forks

47

Language

Python

License

Apache-2.0

Last pushed

Mar 04, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/philipperemy/tensorflow-ctc-speech-recognition"

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