jonatasgrosman's picture
jonatasgrosman/exp_w2v2t_th_hubert_s975
72f21e7
|
raw
history blame
588 Bytes
metadata
language:
  - th
license: apache-2.0
tags:
  - automatic-speech-recognition
  - th
datasets:
  - mozilla-foundation/common_voice_7_0

exp_w2v2t_th_hubert_s975

Fine-tuned facebook/hubert-large-ll60k for speech recognition on Thai using the train split of Common Voice 7.0. When using this model, make sure that your speech input is sampled at 16kHz.

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