sooftware/speech-transformer

Transformer implementation speciaized in speech recognition tasks using Pytorch.

39
/ 100
Emerging

This project offers a foundational building block for creating sophisticated speech recognition systems. It takes raw audio data, typically represented as feature vectors, and transforms it into predicted sequences of spoken words or phonemes. It's intended for machine learning engineers and researchers who are developing custom speech-to-text applications.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher building a custom speech recognition model and need a robust Transformer architecture designed for audio processing.

Not ideal if you need a ready-to-use speech-to-text application or a full training pipeline, as this provides only the model architecture.

speech-recognition natural-language-processing audio-processing machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

65

Forks

11

Language

Python

License

MIT

Last pushed

Nov 28, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/sooftware/speech-transformer"

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