jonatasgrosman's picture
jonatasgrosman/exp_w2v2t_fa_wav2vec2_s873
4ff250d
|
raw
history blame
589 Bytes
metadata
language:
  - fa
license: apache-2.0
tags:
  - automatic-speech-recognition
  - fa
datasets:
  - mozilla-foundation/common_voice_7_0

exp_w2v2t_fa_wav2vec2_s873

Fine-tuned facebook/wav2vec2-large-lv60 for speech recognition using the train split of Common Voice 7.0 (fa). When using this model, make sure that your speech input is sampled at 16kHz.

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