EmotiVoice is a powerful and modern open-source text-to-speech engine. EmotiVoice speaks both English and Chinese, and with over 2000 different voices (refer to the List of Voices for details). The most prominent feature is emotional synthesis, allowing you to create speech with a wide range of emotions, including happy, excited, sad, angry and others.
https://github.com/netease-youdao/EmotiVoice
docker版本占用内存大概3.2G，响应速度非常快。以合成“我挥一挥衣袖，不带走一片云彩”为例，8核CPU需要1.5秒。coqui占用内容大概1.3G，合成同样句子需要大概8.5秒。
如果使用非docker的版本，占用内存1G，合成上面的句子只需要0.6秒，可完美替代Coqui。
启动docker后可以查询conatiner_id：
sudo docker ps
然后进入docker系统：
sudo docker exec -it f2f5831fabd6 /bin/bash
下面命令何以启动demo网页服务：
streamlit run demo_page.pyPackaging code:
pyinstaller --copy-metadata tqdm --copy-metadata regex --copy-metadata requests --copy-metadata packaging --copy-metadata filelock --copy-metadata numpy --copy-metadata tokenizers --copy-metadata torch --hidden-import config server.py
评论