I am going to train a model using my own dataset. The speech files in the dataset are wav files, while the input format for LPCNet is .s16. I am not familiar with the s16 format. Could you please tell me how to batchly change the wav files to s16 files ?
I am going to train a model using my own dataset. The speech files in the dataset are wav files, while the input format for LPCNet is .s16. I am not familiar with the s16 format. Could you please tell me how to batchly change the wav files to s16 files ?