Closed syjunghwang closed 1 year ago
When i learn the audiolm model, there is a code that converts the music input data into a mono type(channel size=1) by averaging when the channel size is 2. Is it impossible to learn by putting stereo sound like music into the model as it is?
When i learn the audiolm model, there is a code that converts the music input data into a mono type(channel size=1) by averaging when the channel size is 2. Is it impossible to learn by putting stereo sound like music into the model as it is?