Wav2Vec2-MyST / README.md
MagicLuke's picture
Update README.md
6d8f754 verified
|
raw
history blame
671 Bytes
metadata
license: mit
language:
  - en

Model Description:

This is the wav2vec2-base model being pre-trained on the My Science Tutor (MyST 470h) dataset (from LDC).

The pertaining is done by using fairseq (wav2vec2_base_librispeech config).

The converge checkpoint is converted from PyTorch model to Hugging Face model by using a modified version of convertor script offered by Huggingface