no message

This commit is contained in:
Calvin 2021-09-11 15:01:18 +08:00
parent 7a4f7f6e3e
commit d5e5bc70ff

View File

@ -40,12 +40,14 @@ SV2TTS工作首先将这两个过程分开通过第一个语音特征编码
运行成功后,命令行应该看到下面的信息:
```text
...
# 测试语音文件:
# src/test/resources/biaobei-009502.mp3
[INFO ] - 文本: 基于给定音色将文本转为梅尔频谱
[INFO ] - 给定音色: src/test/resources/biaobei-009502.mp3
# 生成特征向量:
[INFO ] - embeddings shape: [256]
[INFO ] - embeddings: [0.06272025, 0.0, 0.24136968, ..., 0.035975248, 0.0, 0.106041126, 0.027405139, 0.0, 0.07339379, 0.0]
[INFO ] - Speaker Embedding Shape: [256]
[INFO ] - Speaker Embedding: [0.06272025, 0.0, 0.24136968, ..., 0.027405139, 0.0, 0.07339379, 0.0]
[INFO ] - mel频谱数据 Shape: [80, 331]
[INFO ] - mel频谱数据: [-6.739388, -6.266942, -5.752069, ..., -10.643405, -10.558134, -10.5380535]
```