🎯 ESPnet Leaderboard

Comprehensive benchmarks for speech and language processing models

Welcome to the ESPnet Leaderboard! This platform tracks the performance of various models across different speech and language processing tasks. Navigate through the tabs to explore different task categories.

Speech Recognition Leaderboard

Showing top performing models for speech recognition task

Sub Tasks

LibriSpeech-100h

LibriSpeech ASR corpus 100h subset

Rows per page


1	Darshan7575/librispeech_100_multiconvformer_ctcatt_conv_fusion	0	5.9	16.6	6.2	23.1


1	Darshan7575/librispeech_100_multiconvformer_ctcatt_conv_fusion	5.9	16.6	6.2	17
2	pyf98/librispeech_100_e_branchformer	6.1	16.7	6.3	17
3	pyf98/librispeech_100_transducer_e_branchformer	6.6	17.6	6.8	18
4	pyf98/librispeech_100_ctc_e_branchformer	9.2	22.4	9.6	23.1

Page 1 of 1

Citation

"LibriSpeech: an ASR corpus based on public domain audio books", Vassil Panayotov, Guoguo Chen, Daniel Povey and Sanjeev Khudanpur, ICASSP 2015 (submitted)