hirofumi0810/neural_sp

End-to-end ASR/LM implementation with PyTorch

51
/ 100
Established

NeuralSP helps researchers and engineers build advanced speech recognition and natural language processing systems. It takes raw audio data or text corpora and produces trained models capable of transcribing speech to text or generating human-like text. This tool is for those working in speech technology development, computational linguistics, or AI research to create custom speech solutions.

594 stars. No commits in the last 6 months.

Use this if you need to experiment with state-of-the-art neural network architectures for building highly accurate Automatic Speech Recognition (ASR) systems or Language Models (LMs).

Not ideal if you're looking for a simple, out-of-the-box speech-to-text application without needing to understand or customize the underlying neural network models.

speech-recognition natural-language-processing machine-learning-research audio-processing computational-linguistics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

594

Forks

136

Language

Python

License

Apache-2.0

Last pushed

Aug 30, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/hirofumi0810/neural_sp"

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