public/model-sense-voice-small
38
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
北念 2024-06-27 20:46:29 +08:00
parent 0652ca1af5
commit fbe5bf1d21
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
README.md
View File

@ -63,10 +63,13 @@ SenseVoice多语言音频理解模型，支持语音识别、语种识别、语
<img src="fig/sensevoice.png" alt="SenseVoice模型结构" width="500" /> <img src="fig/sensevoice.png" alt="SenseVoice模型结构" width="500" />
</p> </p>
SenseVoice-Small是基于非自回归端到端框架模型，为了指定任务，我们在语音特征前添加四个嵌入作为输入传递给编码器：
- <LID>：用于预测音频语种标签。
- <SER>：用于预测音频情感标签。
- <AED>：用于预测音频包含的事件标签。
- <ITN>：用于指定识别输出文本是否进行逆文本正则化。
# 用法
# 用法 # 用法
## 推理 ## 推理