Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Speech Recognition on LibriSpeech (100h)
Loading...
6.2
WER (%)
Li-GRU
6.076
6.913
7.75
8.587
Nov 19, 2018
Feb 21, 2020
May 26, 2021
Aug 29, 2022
Dec 2, 2023
Mar 6, 2025
Jun 9, 2026
WER (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
WER (%)
Li-GRU
Toolkit=PyTorch-Kaldi,...
2018.11
6.2
GRU
Toolkit=PyTorch-Kaldi,...
2018.11
6.3
LSTM
Toolkit=PyTorch-Kaldi,...
2018.11
6.4
MLP
Toolkit=PyTorch-Kaldi,...
2018.11
6.5
p-norm Kaldi baseline
Subset=100h
2018.11
6.5
Whisper-M + Llama 8B (4bit, r=4)
Train=Joint, Decode=PF...
2026.06
6.8
Whisper-M + Llama 8B (4bit, r=4)
Train=Joint, Decode=S2T
2026.06
7
Whisper-M + Llama 8B (4bit, r=4)
Train=S2T, Decode=S2T
2026.06
7.3
Whisper-M + Llama 8B (4bit, r=4)
Train=PF-S2T, Decode=P...
2026.06
7.6
Whisper-M
Train=–, Decode=Beam
2026.06
9.3
Feedback
Search any
task
Search any
task