I need a Pytorch expert to train a transformer (Hugging face) with audio files. The training should be reading audio files, tokenizing, then a pretrained model should be trained on classification 5 classes.
Please apply if you have experience with Pytorch and Hugging face. I have some codes you can modify
Hi, I can finetune the wav2vec2 Huggingface pretrained model for your speech recognition dataset. Do you have labelled data? Also, the audio files are english or any other language? Can we discuss?