List your company

Handwritten Text Recognition on IAM Aachen (test)

2.26CERDRetHTRBASE
2.09443.21224.335.4478Feb 19, 2026

Evaluation results

MethodLinks
DRetHTRBASEParams=107M, Encoder=–, Decoder=RetNet w/EN-V2, L12/h12/d768, Train=Syn+IAM, LM=No2026.022.26
DRetHTR_BASEParams=107M, Tokenization=Character Level, Total Tokens=442832, Inference Time=123s, Memory=22.14GB2026.022.26
DTrHTR_BASEParams=107M, Tokenization=Character Level, Total Tokens=442832, Inference Time=233s, Memory=36.25GB2026.022.35
DTrOCRParams=105M, Encoder=–, Decoder=GPT-2, L12/h12/d768, Train=Syn+IAM, LM=No2026.022.38
Diaz et al.Params=1.5M, Encoder=SelfAttn, L16/h4/d256, Decoder=CTC, Train=Int.+IAM, LM=Yes2026.022.75
TrOCRLARGEParams=558M, Encoder=BEiTLARGE, L24/h16/d1024, Decoder=RoBERTaLARGE, L12/h16/d1024, Train=Syn+IAM, LM=No2026.022.89
TrOCR_LARGEParams=558M, Tokenization=BPE(GPT-2) |V| = 50,257, Total Tokens=31959, Inference Time=2725s, Memory=13.5GB2026.022.89
DRetHTRSMALLParams=73M, Encoder=–, Decoder=RetNet w/EN-V2, L4/h8/d1024, Train=Syn+IAM, LM=No2026.022.97
DRetHTR_SMALLParams=73M, Tokenization=Character Level, Total Tokens=442832, Inference Time=67s, Memory=14.5GB2026.022.97
DTrHTR_SMALLParams=73M, Tokenization=Character Level, Total Tokens=442832, Inference Time=110s, Memory=25.1GB2026.022.98
DRetHTR_SMALLParams=74M, Tokenization=BPE |V| = 500, Total Tokens=49574, Inference Time=44s, Memory=14.9GB2026.023.01
DTrHTR_SMALLParams=74M, Tokenization=BPE |V| = 500, Total Tokens=49574, Inference Time=69s, Memory=23.9GB2026.023.01
Bluche and MessinaParams=0.75M, Encoder=GCRNN, 6Conv+2BiLSTM, d128, Decoder=CTC, Train=Syn+IAM, LM=No2026.023.2
TrOCR_BASEParams=334M, Tokenization=BPE(GPT-2) |V| = 50,257, Total Tokens=31959, Inference Time=1717s, Memory=12.3GB2026.023.42
TrOCR_SMALLParams=62M, Tokenization=BPE(GPT-2) |V| = 50,257, Total Tokens=31959, Inference Time=310s, Memory=9.1GB2026.024.22
DRetHTRSMALLParams=73M, Encoder=–, Decoder=RetNet w/EN-V2, L4/h8/d1024, Train=IAM, LM=No2026.024.35
PuigcerverParams=≈8.3M, Encoder=5Conv, Decoder=5×BiLSTM d256 + CTC, Train=IAM, LM=Yes2026.024.4
VANParams=2.7M, Encoder=18 VGG-style Conv, Decoder=1×LSTM d256 + CTC, Train=IAM, LM=No2026.024.45
Kang et al.Params=100M, Encoder=Tx w/ResNet50, L4/h8/d1024, Decoder=Tx, L4/h8/d1024, Train=Syn+IAM, LM=No2026.024.67
HTR-VTParams=53.5M, Encoder=ResNet18 + Tx-Enc, L4/h6/d768, Decoder=CTC, Train=IAM, LM=No2026.024.7
Michael et al.Params=≈1.8M, Encoder=3Conv+3BLSTM, d256, Decoder=Attn-LSTM, L1/d256, Train=IAM, LM=No2026.024.87
Wick et al.Params=≈22M, Encoder=3Conv + Tx, L3/h8/d512, Decoder=Bidi Tx, L3/h8/d512, Train=IAM, LM=No2026.025.67
DANParams=≈2.18M, Encoder=23Conv+GRU, Decoder=GRU, L1/d256, Train=IAM, LM=No2026.026.4