asr-wav2vec2-large-xlsr-53-russian

Audio transcription model for converting Russian audio to Russian text

Notes

huggingface model id: jonatasgrosman/wav2vec2-large-xlsr-53-russian

Wav2Vec2-Large-XLSR-53-Russian

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Russian using the Common Voice and CSS10. When using this model, make sure that your speech input is sampled at 16kHz.

This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud :)

The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint

  • ID
  • Model Type ID
    Audio To Text
  • Description
    Audio transcription model for converting Russian audio to Russian text
  • Last Updated
    Jun 28, 2022
  • Privacy
    PUBLIC
  • Toolkit
  • License
  • Share
    • Badge
      asr-wav2vec2-large-xlsr-53-russian