Models / jonatasgrosman / Wav2Vec2 Large XLSR-53 Russian

Wav2Vec2 Large XLSR-53 Russian

audio

A fine-tuned Wav2Vec2 model for Russian speech recognition, based on Facebook's XLSR-53 pretrained checkpoint.

audio

homepage ↗docs ↗

Specs

Context & limits

—

context window

—

max output

Lifecycle

Dates

released2021-06-01

Resources

homepagehttps://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-russian ↗

docshttps://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-russian ↗