Original link: https://v3u.cn/a_id_311
The pop queen Stefanie Sun’s timbre is of course excellent, but at present the entire Internet is reproducing her voice, and it is inevitable that she will feel a little tired after listening to it too much. After searching the Internet, I have not found a timbre model of a folk singer. That’s it, what we can’t get is always a commotion. This time we build our own training set to create our own timbre model, and let the goddess of folk songs sing pop songs, as much as we want. Building a training set A training set refers to a collection of data used to train a neural network model. This data set usually consists of a large number of inputs and corresponding outputs. The neural network model is trained by learning the relationship between the input and the output, and the parameters of the model are adjusted during the training process to minimize the error. In layman’s terms, if we want to train the timbre model of folk singer Ye Bei, we need to use her songs as input parameters, that is, the training set. The role of the training set is to provide learning materials for the model so that it can learn from the input data. …
This article is transferred from: https://v3u.cn/a_id_311
This site is only for collection, and the copyright belongs to the original author.