Help Center/ ModelArts/ ModelArts User Guide (Standard)/ Using ExeML for Zero-Code AI Development/ Using ExeML for Sound Classification/ Training a Sound Classification Model
Updated on 2024-10-29 GMT+08:00
View PDF
Share

Training a Sound Classification Model

After labeling the sound files, train a model. You can perform model training to obtain the required sound classification model. Training sound files must be classified into at least two classes, and each class must contain at least five sound files.

Procedure

Before starting the training, label data and then perform auto training.

  1. On the ExeML page of the new version, click the name of the target project. Then, click Instance Details on the labeling phase to label data.
  2. Return to the labeling phase of the new-version ExeML, click Next and wait until the workflow enters the training phase.
  3. Wait until the training is complete. No manual operation is required. If you close or exit the page, the system continues training until it is complete.
  4. On the sound classification phase, wait until the training status changes from Running to Executed.
  5. After the training, click on the sound classification phase to view metric information.
    Table 1 Evaluation result parameters

    Parameter

    Description

    Recall

    Fraction of correctly predicted samples over all samples predicted as a class. It shows the ability of a model to distinguish positive samples.

    Precision

    Fraction of correctly predicted samples over all samples predicted as a class. It shows the ability of a model to distinguish negative samples.

    Accuracy

    Fraction of correctly predicted samples over all samples. It shows the general ability of a model to recognize samples.

    F1 Score

    Harmonic average of the precision and recall of a model. It is used to evaluate the quality of a model. A high F1 score indicates a good model.

An ExeML project supports multiple rounds of training, and each round generates an AI application version. For example, the first training version is 0.0.1, and the next version is 0.0.2. The trained models can be managed by training version. After the trained model meets your requirements, deploy the model as a service.