wav2vec2-large-xlsr-53-polish

jonatasgrosman/wav2vec2-large-xlsr-53-polish is an automatic speech recognition (ASR) model fine-tuned from facebook/wav2vec2-large-xlsr-53 for the Polish language.

Key Strengths

• Trained on the train and validation splits of Common Voice 6.1.
• Can be used directly without a language model for decoding.
• Requires input speech sampled at 16 kHz.

Best For

Polish speech-to-text applications where a dedicated, fine-tuned wav2vec2 model is desired. Suitable for general dictation, transcription of read speech, and similar tasks within the Common Voice domain.

Model citation (BibTeX):

@misc{grosman2021xlsr53-large-polish,
  title={Fine-tuned {XLSR}-53 large model for speech recognition in {P}olish},
  author={Grosman, Jonatas},
  howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-polish}},
  year={2021}
}