# Danish speech recognition

Roest Wav2vec2 1B V2
Openrail
This is Denmark's most advanced speech recognition model, trained by Alvenir as part of the CoRal project, based on the CoRal-v2 dataset, covering various Danish dialects.
Speech Recognition Other
R
CoRal-project
91
1
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
Hviske Tiske
Openrail
Currently the fastest Danish ASR model, a distilled version of hviske-v2, achieving approximately 4x speed improvement while maintaining the same accuracy.
Speech Recognition Other
H
pluttodk
139
5
Whisper Medium Da
Apache-2.0
A Danish automatic speech recognition (ASR) model fine-tuned based on OpenAI Whisper Medium, trained on Common Voice 11 and FLEURS datasets
Speech Recognition Transformers Other
W
jstoone
22
5
Dansk Wav2vec21
Apache-2.0
This model is a Danish speech recognition model fine-tuned by Siyam/SKYLy on the common_voice dataset
Speech Recognition Transformers
D
Siyam
32
0
Wav2vec2 Base Da Ft Nst
Apache-2.0
Danish speech recognition model fine-tuned on the NST dataset, supporting 16kHz sampled audio input
Speech Recognition Transformers Other
W
Alvenir
15
3
Wav2vec2 Xls R 300m Ftspeech
Other
A Danish automatic speech recognition model fine-tuned on Danish parliamentary speech dataset based on facebook/wav2vec2-xls-r-300m
Speech Recognition Transformers Other
W
saattrupdan
1.3M
0
Wav2vec2 Base Da Voxpopuli V2
A speech model based on Facebook's Wav2Vec2 architecture, specifically pre-trained for Danish using 13.6k unlabeled data from the VoxPopuli corpus.
Speech Recognition Transformers Other
W
facebook
35
0
Wav2vec2 Large Xls R 300m Da Colab
Apache-2.0
A Danish speech recognition model fine-tuned based on Alvenir/wav2vec2-base-da, suitable for Danish speech-to-text tasks
Speech Recognition Transformers
W
vachonni
16
0
Kblab Voxrex Wav2vec2 Large Cv8 Da
A speech recognition model fine-tuned on the Danish portion of Common Voice 8.0 based on a Swedish acoustic model
Speech Recognition Transformers Other
K
saattrupdan
23
1
Wav2vec2 Xls R 300m Cv8 Da
Apache-2.0
A speech recognition model fine-tuned on Common Voice 8.0 Danish data based on facebook/wav2vec2-xls-r-300m
Speech Recognition Transformers Other
W
saattrupdan
13
0
Alvenir Wav2vec2 Base Cv8 Da
Apache-2.0
A Danish acoustic model fine-tuned on the Danish portion of Common Voice 8.0 data for speech recognition
Speech Recognition Transformers Other
A
saattrupdan
21
0
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase