Modelpublic

jonatasgrosman/exp_w2v2t_sv-se_xlsr-53_s131

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face

0likes12downloads

Model Card

expw2v2tsv-sexlsr-53s131

Fine-tuned facebook/wav2vec2-large-xlsr-53 for speech recognition using the train split of Common Voice 7.0 (sv-SE). When using this model, make sure that your speech input is sampled at 16kHz.

This model has been fine-tuned by the HuggingSound tool.