How to use unk_token (unknown token) during wav2vec model finetuning

[Su-Youn]

@patrickvonplaten Thanks for your reply and advice. I also found you and pcueng’s discussion about Spanish ASR with out-of-vocabulary (non-spanish character handling) in the transcriptions. I linked this just in case other people may be interested. Thank you for discussions.

Spanish ASR: Fine-Tuning Wav2Vec2

Hey @pcuenq, Very good question & It’s great that you already took a look at the dataset. I think you have the following three options here: Remove all characters which clearly don’t belong to the Spanish languages from both the training and the test data. Don’t remove those characters from the training and test dataset, but remove them from the vocabulary. In this scenario make sure to add the "[UNK]" token to the vocab and define it as unk_token="[UNK]" when instantiating the tokenizer.…