Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
huolongshe 54a3be8701 | 2 months ago | |
---|---|---|
app | 8 months ago | |
docs | 8 months ago | |
.gitignore | 8 months ago | |
Dockerfile | 8 months ago | |
LICENSE | 8 months ago | |
README.md | 2 months ago | |
application.yml | 8 months ago | |
build-docker.sh | 8 months ago | |
pack_model.py | 8 months ago | |
pip-install-reqs.sh | 8 months ago | |
requirements.txt | 8 months ago | |
run_model_server.py | 8 months ago |
Controllable Time-delay Transformer VAD Realtime 是达摩院语音团队提出的实时后处理框架中的标点模块,在中文标点预测通用模型 基础上针对ASR流式场景,提供了一种以VAD点为实时调用点的流式调用方式。可以被应用于流式语音识别场景中的后处理步骤,协助语音识别模块输出具有可读性的文本结果。
常规的Transformer会依赖很远的未来信息,导致长时间结果不固定。Controllable Time-delay Transformer VAD Realtime 通过对VAD前后文本作局部遮蔽处理,使得标点能获得有效的历史信息,同时又不会改变历史结果。在效果无损的情况下,有效控制标点的延时,提升上屏效果,降低链路集成复杂度。
模型来源: https://modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727/summary
本模型基于 ServiceBoot微服务引擎 进行服务化封装,参见: 《CubeAI模型开发指南》
$ sh pip-install-reqs.sh
$ serviceboot start
或
$ python3 run_model_server.py
一键式本地容器化部署和运行,参见: 《CubeAI模型独立部署指南》 或 CubeAI Docker Builder
本模型服务可一键发布至 CubeAI智立方平台 进行共享和部署,参见: 《CubeAI模型发布指南》
No Description
Python Shell Text Dockerfile
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》