pre-train model
#1
by
sjhu
- opened
Hi, as the intro said "Wav2Vec2-Conformer with relative position embeddings, pre-trained and fine-tuned on 960 hours of Librispeech on 16kHz sampled speech audio", but in the Github readme, the pre-train dataset is Libri-Light.
Which one is correct?
Hi @sjhu . The model is pre-trained on LibriVox 60k and fine-tuned on Librispeech 960h.
Addressed in #2.