HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Speech Recognition On Librispeech Test Other

Metrics

Word Error Rate (WER)

Results

Performance results of various models on this benchmark

Paper Title
Local Prior Matching (Large Model)20.84Semi-Supervised Speech Recognition via Local Prior Matching
Snips16.5Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
Local Prior Matching (Large Model, ConvLM LM)15.28Semi-Supervised Speech Recognition via Local Prior Matching
Deep Speech 213.25Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
TDNN + pNorm + speed up/down speech12.5-
CTC-CRF 4gram-LM10.65CRF-based Single-stage Acoustic Modeling with CTC Topology
Convolutional Speech Recognition10.47Fully Convolutional Speech Recognition
MT4SSL9.6MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets
Jasper DR 10x58.79Jasper: An End-to-End Convolutional Neural Acoustic Model
Espresso8.7Espresso: A Fast End-to-end Neural Speech Recognition Toolkit
Jasper DR 10x5 (+ Time/Freq Masks)7.84Jasper: An End-to-End Convolutional Neural Acoustic Model
tdnn + chain + rnnlm rescoring7.63Neural Network Language Modeling with Letter-based Features and Importance Sampling
QuartzNet15x57.25QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions
Conformer with Relaxed Attention6.85Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition
LAS (no LM)6.5SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Squeezeformer (L)5.97Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
LAS + SpecAugment5.8SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Multi-Stream Self-Attention With Dilated 1D Convolutions5.80State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions
Transformer5.7A Comparative Study on Transformer vs RNN in Speech Applications
LSTM Transducer5.6Librispeech Transducer Model with Internal Language Model Prior Correction
0 of 53 row(s) selected.
Speech Recognition On Librispeech Test Other | SOTA | HyperAI