holm-aune-bachelor2018/ctc

Speech recognition with CTC in Keras with Tensorflow backend

41
/ 100
Emerging

This project helps researchers and machine learning engineers explore different neural network architectures for converting spoken audio into written text. You feed it large datasets of speech recordings and their corresponding transcripts, and it produces a trained model that can automatically transcribe new audio. It's designed for those working on academic projects or proof-of-concept speech recognition systems.

No commits in the last 6 months.

Use this if you are a researcher or ML engineer who wants to experiment with different recurrent neural network (RNN) and Connectionist Temporal Classification (CTC) configurations for speech recognition.

Not ideal if you need a ready-to-use speech-to-text application or a solution for production-scale speech transcription without deep technical configuration.

speech-to-text automatic-speech-recognition natural-language-processing machine-learning-research audio-transcription
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

31

Forks

15

Language

Python

License

GPL-3.0

Last pushed

Mar 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/holm-aune-bachelor2018/ctc"

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