# Swedish speech recognition

Kb Whisper Tiny
Apache-2.0
A Whisper model released by the National Library of Sweden, optimized for Swedish speech recognition, significantly reducing the error rate compared to the original OpenAI version.
Speech Recognition Transformers Other
K
KBLab
1,791
2
Kb Whisper Small
Apache-2.0
Whisper model released by the Swedish National Library, optimized for Swedish, trained on 50,000+ hours of Swedish speech data, outperforming the original OpenAI version
Speech Recognition Transformers Other
K
KBLab
28.61k
3
Kb Whisper Medium
Apache-2.0
A Whisper model trained on over 50,000 hours of Swedish speech data released by the National Library of Sweden, excelling in Swedish speech recognition tasks
Speech Recognition Transformers Other
K
KBLab
691
3
Kb Whisper Large
Apache-2.0
A Swedish speech recognition model based on the Whisper architecture released by the National Library of Sweden. The training data exceeds 50,000 hours, significantly reducing the word error rate.
Speech Recognition Transformers Other
K
KBLab
8,880
42
Exp W2v2t Sv Se Vp Nl S842
Apache-2.0
This is a Swedish automatic speech recognition model fine-tuned based on the facebook/wav2vec2-large-nl-voxpopuli model, trained using the Common Voice 7.0 (sv-SE) dataset.
Speech Recognition Transformers
E
jonatasgrosman
16
0
Exp W2v2t Sv Se Wavlm S42
Apache-2.0
A Swedish automatic speech recognition model fine-tuned from microsoft/wavlm-large, suitable for 16kHz sampled audio input.
Speech Recognition Transformers
E
jonatasgrosman
20
0
Wav2vec2 Large Voxrex Swedish 4gram
This is a model for Swedish automatic speech recognition (ASR), combining the VoxRex-C acoustic model with a 4-gram language model based on social media data.
Speech Recognition Transformers Other
W
viktor-enzell
5,891
5
Wav2vec2 Common Voice Tr Demo
Apache-2.0
This model is an automatic speech recognition (ASR) model fine-tuned on the COMMON_VOICE SV-SE dataset based on facebook/wav2vec2-large-xlsr-53, supporting Swedish speech recognition.
Speech Recognition Transformers
W
birgermoell
17
0
Xls R 300 Sv Cv7
Apache-2.0
This is an automatic speech recognition model fine-tuned on the Swedish Common Voice 7.0 dataset based on facebook/wav2vec2-xls-r-300m
Speech Recognition Transformers Other
X
patrickvonplaten
19
0
Wav2vec2 Large Xls R 1b Swedish
Apache-2.0
This model is an automatic speech recognition model fine-tuned on the Common Voice Swedish dataset based on facebook/wav2vec2-xls-r-1b, supporting Swedish speech-to-text tasks.
Speech Recognition Transformers Other
W
kingabzpro
844
1
Wav2vec2 Base Sv Voxpopuli
A Wav2Vec2 base model pretrained on the Swedish subset of the VoxPopuli corpus, suitable for Swedish speech recognition tasks.
Speech Recognition Transformers Other
W
facebook
33
0
Wav2vec2 Base Sv Voxpopuli V2
A speech model based on Facebook's Wav2Vec2 architecture, specifically pre-trained for Swedish using 16.3k hours of unlabeled data from the VoxPopuli corpus.
Speech Recognition Transformers Other
W
facebook
30
0
Wav2vec2 Speechdat
Apache-2.0
This model is a Swedish automatic speech recognition model fine-tuned on the COMMON_VOICE - SV-SE dataset based on facebook/wav2vec2-large-xlsr-53.
Speech Recognition Transformers
W
birgermoell
29
0
Xls R 300m Sv Robust
This is an automatic speech recognition model fine-tuned on the Swedish Common Voice dataset based on KBLab/wav2vec2-large-voxrex
Speech Recognition Transformers Other
X
marinone94
27
1
Xls R 300m It Cv8
This model is a speech recognition model fine-tuned on the Common Voice Swedish dataset based on facebook/wav2vec2-xls-r-300m, achieving a word error rate (WER) of 1.0286 on the evaluation set.
Speech Recognition Transformers
X
masapasa
19
1
Wav2vec2 Large Xlsr Swedish
Apache-2.0
This is a Swedish automatic speech recognition model based on the XLSR-53 architecture, fine-tuned on the Common Voice dataset.
Speech Recognition Other
W
marma
24
0
Xls R 300m Sv
Apache-2.0
Automatic speech recognition model fine-tuned on Swedish dataset based on facebook/wav2vec2-xls-r-300m
Speech Recognition Transformers Other
X
hf-test
28
3
Wav2vec2 Swedish Common Voice
Apache-2.0
This is a speech recognition model fine-tuned on the Swedish Common Voice dataset based on the facebook/wav2vec2-large-xlsr-53 model, with a training data volume of 402MB.
Speech Recognition Other
W
birgermoell
24
1
Wav2vec2 Large Voxrex Swedish
A Swedish automatic speech recognition model fine-tuned based on the VoxRex large model, supporting 16kHz sampling rate audio input
Speech Recognition Transformers Other
W
KBLab
101.28k
12
Wav2vec2 Large Xlsr 53 Swedish
Apache-2.0
A Swedish automatic speech recognition model fine-tuned based on the facebook/wav2vec2-large-xlsr-53 framework, supporting 16kHz sampled audio input
Speech Recognition Other
W
KBLab
30.51k
3
Wav2vec2 Large Xlsr 53 Swedish
Apache-2.0
This is an automatic speech recognition (ASR) model fine-tuned on the Swedish Common Voice dataset, based on the facebook/wav2vec2-large-xlsr-53 model.
Speech Recognition
W
MehdiHosseiniMoghadam
24
0
Wav2vec2 Base Voxpopuli Sv Swedish
A Swedish speech recognition model fine-tuned using NST and Common Voice data, based on Facebook's VoxPopuli-sv base model.
Speech Recognition Transformers
W
KBLab
38
0
Wav2vec2 Large Voxpopuli Sv Swedish
This model is based on Facebook's VoxPopuli-sv large model, additionally pre-trained and fine-tuned using Swedish radio programs, NST, and Common Voice data.
Speech Recognition
W
KBLab
38.78k
0
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase