Benchmark	Methodology	Metrics
distant-speech-recognition-on-dirha-english	Li-GRU	Word Error Rate (WER): 23.9
noisy-speech-recognition-on-chime-real	Li-GRU	Percentage error: 14.6
speech-recognition-on-librispeech-test-clean	Li-GRU	Word Error Rate (WER): 6.2
speech-recognition-on-timit	Li-GRU	Percentage error: 16.3
speech-recognition-on-timit	LSTM + Dropout + BatchNorm + Monophone Reg	Percentage error: 14.5
speech-recognition-on-timit	LiGRU + Dropout + BatchNorm + Monophone Reg	Percentage error: 14.2
speech-recognition-on-timit	LSTM	Percentage error: 16.0
speech-recognition-on-timit	GRU + Dropout + BatchNorm + Monophone Reg	Percentage error: 14.9
speech-recognition-on-timit	RNN + Dropout + BatchNorm + Monophone Reg	Percentage error: 15.9
speech-recognition-on-timit	GRU	Percentage error: 16.6
speech-recognition-on-timit	RNN	Percentage error: 16.5

Build AI with AI

From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.

AI Co-coding

Ready-to-use GPUs

Best Pricing

Hyper Newsletters

Subscribe to our latest updates

We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning