# Low Character Error Rate
Phi 4 Multimodal Instruct Commonvoice Zh Tw
MIT
A Taiwanese Mandarin speech recognition model fine-tuned from microsoft/Phi-4-multimodal-instruct, trained on the Taiwanese Mandarin General Voice 19.0 dataset
Audio-to-Text
Transformers Chinese

P
JacobLinCool
28
1
Japanese Wav2vec2 Large Rs35kh
Apache-2.0
A Japanese automatic speech recognition model fine-tuned on the large-scale Japanese ASR corpus ReazonSpeech v2.0, based on the wav2vec 2.0 Large architecture
Speech Recognition
Transformers Japanese

J
reazon-research
244
1
Belle Whisper Large V2 Zh
Apache-2.0
A Chinese speech recognition model fine-tuned based on whisper-large-v2, achieving a 30-70% relative performance improvement in multiple Chinese speech recognition benchmarks.
Speech Recognition
Transformers

B
BELLE-2
140
33
Trocr Base Handwritten OCR Handwriting Recognition V2
A fine-tuned handwritten OCR model based on Microsoft's trocr-base-handwritten, achieving a character error rate (CER) of 0.0360 on the evaluation set
Text Recognition
Transformers English

T
DunnBC22
269
16
Trocr Base Printed License Plates Ocr
An OCR model fine-tuned based on microsoft/trocr-base-printed, specifically designed for license plate text recognition
Text Recognition
Transformers English

T
DunnBC22
517
9
Xls R Et
Apache-2.0
Estonian automatic speech recognition model fine-tuned on the wav2vec2-xls-r-300m architecture, trained on the Common Voice 7.0 dataset
Speech Recognition
Transformers Other

X
shpotes
23
0
XLSR 300M Nynorsk
Apache-2.0
A Nynorsk automatic speech recognition model based on the XLSR-300M architecture, trained on the NPSC dataset with low word error rate and character error rate.
Speech Recognition
Transformers

X
NbAiLab
22
0
Featured Recommended AI Models