kaituoxu/Speech-Transformer
A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.
Implements end-to-end ASR by directly mapping acoustic features to character sequences without intermediate phoneme representations. Leverages Kaldi for feature extraction and integrates with Visdom for real-time loss visualization during training. Demonstrates competitive character error rates (12.8% CER) on the AISHELL Mandarin dataset compared to LSTM and attention-based baselines.
809 stars. No commits in the last 6 months.
Stars
809
Forks
196
Language
Python
License
—
Category
Last pushed
Apr 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/kaituoxu/Speech-Transformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
srvk/eesen
The official repository of the Eesen project