maetshju/flux-blstm-implementation

An implementation of the Graves & Schmidhuber (2005) bidirectional LSTM in Flux.

35
/ 100
Emerging

This project helps speech recognition researchers and engineers who need to classify phonemes from audio recordings. It takes raw speech audio as input and outputs framewise phoneme classifications. This is specifically for those working on advanced speech processing systems.

No commits in the last 6 months.

Use this if you are developing a speech recognition system and need an established, high-performance method for classifying individual speech sounds within audio frames.

Not ideal if you are looking for a general-purpose speech-to-text solution or a simpler machine learning model for different types of sequential data.

speech-recognition phoneme-classification audio-processing neural-networks linguistics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

11

Forks

3

Language

Julia

License

MIT

Last pushed

May 14, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/maetshju/flux-blstm-implementation"

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