When synthesizing the following sentence, the first two words "Self-attention" come out with very low volume at the beginning, for unknown reasons. This issue occurs with the "heart" voice. When switching to other voices, some exhibit the same issue while others do not.
Text: "Self-attention, sometimes called intra-attention is an attention mechanism relating different positions of a single sequence in order to compute a representation of the sequence."
When synthesizing the following sentence, the first two words "Self-attention" come out with very low volume at the beginning, for unknown reasons. This issue occurs with the "heart" voice. When switching to other voices, some exhibit the same issue while others do not.
Text: "Self-attention, sometimes called intra-attention is an attention mechanism relating different positions of a single sequence in order to compute a representation of the sequence."