Speech Recognition On Librispeech Test Other

评估指标

Word Error Rate (WER)

评测结果

各个模型在此基准测试上的表现结果

模型名称	Word Error Rate (WER)	Paper Title	Repository
Espresso	8.7	Espresso: A Fast End-to-end Neural Speech Recognition Toolkit
Jasper DR 10x5 (+ Time/Freq Masks)	7.84	Jasper: An End-to-End Convolutional Neural Acoustic Model
Conv + Transformer AM (ConvLM with Transformer Rescoring) (LS only)	5.18	End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
ContextNet(L)	4.1	ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
SAMBA ASR	2.48	Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models	-
LAS + SpecAugment	5.8	SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Jasper DR 10x5	8.79	Jasper: An End-to-End Convolutional Neural Acoustic Model
Convolutional Speech Recognition	10.47	Fully Convolutional Speech Recognition	-
FAdam	2.49	FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information
Conv + Transformer AM + Iterative Pseudo-Labeling (n-gram LM + Transformer Rescoring)	3.83	Iterative Pseudo-Labeling for Speech Recognition	-
Conformer(M)	4.3	Conformer: Convolution-augmented Transformer for Speech Recognition
Multi-Stream Self-Attention With Dilated 1D Convolutions	5.80	State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions
ContextNet(M)	4.5	ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
HuBERT with Libri-Light	2.9	HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units	-
Zipformer+pruned transducer w/ CR-CTC (no external language model)	3.95	CR-CTC: Consistency regularization on CTC for improved speech recognition
Local Prior Matching (Large Model, ConvLM LM)	15.28	Semi-Supervised Speech Recognition via Local Prior Matching
MT4SSL	9.6	MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets
Conformer(S)	5.0	Conformer: Convolution-augmented Transformer for Speech Recognition
Branchformer + GFSA	4.94	Graph Convolutions Enrich the Self-Attention in Transformers!
Zipformer+CR-CTC (no external language model)	4.35	CR-CTC: Consistency regularization on CTC for improved speech recognition

0 of 53 row(s) selected.