# Low CER performance

Roest Wav2vec2 315m V2
Openrail
Denmark's state-of-the-art speech recognition model trained by Alvenir, based on the CoRal-v2 dataset, supporting multiple Danish dialects
Speech Recognition Safetensors Other
R
CoRal-project
238
2
Japanese Wav2vec2 Base Rs35kh
Apache-2.0
A wav2vec 2.0 Base model fine-tuned on the large-scale Japanese automatic speech recognition corpus ReazonSpeech v2.0, suitable for Japanese automatic speech recognition tasks.
Speech Recognition Transformers Japanese
J
reazon-research
3,968
1
Wav2vec2 Large Xlsr 53 Japanese
Apache-2.0
Japanese speech recognition model fine-tuned from facebook/wav2vec2-large-xlsr-53, supporting 16kHz sampled audio input
Speech Recognition Transformers Japanese
W
Ivydata
19
4
Whisper Large Et
Estonian speech recognition model fine-tuned from OpenAI Whisper-large-v2, developed by Tallinn University of Technology, trained on approximately 1,200 hours of data
Speech Recognition Transformers Other
W
TalTechNLP
245
5
Wav2vec2 Xls R 1b French
Apache-2.0
This is a French automatic speech recognition model based on the XLS-R 1B architecture, fine-tuned on multiple French speech datasets.
Speech Recognition Transformers French
W
jonatasgrosman
379
8
Wav2vec2 Xlsr Estonian
Apache-2.0
This is an automatic speech recognition model fine-tuned on Estonian datasets based on the facebook/wav2vec2-xls-r-1b model.
Speech Recognition Transformers Other
W
sammy786
21
1
Wav2vec2 Xls R 1b Ca Lm
Apache-2.0
This is a Catalan speech recognition model fine-tuned from facebook/wav2vec2-xls-r-300m, trained on multiple Catalan datasets.
Speech Recognition Transformers Other
W
PereLluis13
3,758
4
Wav2vec2 Xls R Sl A2
Apache-2.0
This is an automatic speech recognition model fine-tuned on the Slovenian language dataset (MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - SL) based on the facebook/wav2vec2-xls-r-300m model.
Speech Recognition Transformers Other
W
DrishtiSharma
24
0
Wav2vec2 Xls R 300m Hi Final
Apache-2.0
Hindi speech recognition model fine-tuned from facebook/wav2vec2-xls-r-300m, trained on Openslr multilingual corpus and Common Voice 7.0 dataset
Speech Recognition Transformers Other
W
LegolasTheElf
14
0
Central Kurdish Xlsr
Apache-2.0
This is an automatic speech recognition model fine-tuned on the Central Kurdish dialect based on the facebook/wav2vec2-xls-r-300m model, trained on the Common Voice 8.0 dataset.
Speech Recognition Transformers Other
C
Akashpb13
45
4
Wav2vec2 Xls R 300m Kk N2
Apache-2.0
This is an automatic speech recognition (ASR) model fine-tuned on Kazakh (KK) speech datasets based on the facebook/wav2vec2-xls-r-300m model.
Speech Recognition Transformers Other
W
DrishtiSharma
15
1
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase