hirofumi0810/neural_sp
End-to-end ASR/LM implementation with PyTorch
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.
Stars
594
Forks
136
Language
Python
License
Apache-2.0
Category
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.
Related tools
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project