Open tranmanhdat opened 3 years ago
i have 2 questions, First, is wav2vec lastest model you implement better than wav2vec + wav2letter ( for example in wer, recognition in reality?) Second, can you provide tutorial for training from scratch wav2vec+wav2letter?
i have 2 questions, First, is wav2vec lastest model you implement better than wav2vec + wav2letter ( for example in wer, recognition in reality?) Second, can you provide tutorial for training from scratch wav2vec+wav2letter?