This is continue for Coqui Cantonese Development Notes
可汗学院的教程:https://www.khanacademy.org/math/multivariable-calculus,这是目前找到最好的教程,是文本的,适当地方有习题。(AP是面向高中生的,讲得会不够深入。MIT开放出来的视频是几十年的,质量太差,看着难受。网易公开课里清华的废话比较多,东西比较旧。可汗学院的鼠标视频看着也是很难受的,像素太低,等号大于号有时都分不清。)
矢量与矩阵(vectors and matrics)
点乘(dot product)就像是计算合力,点乘的结果是标量。
叉乘(cross product)的方向要用右手定则,值是面积。有点像计算电磁感应。叉乘的结果是矢量。叉乘只适用于三维矢量。
行列式(determinant)这个名次的翻译不是特别直观,它反映了坐标经过一系列转换后的一个缩放系数,绝对值大于1是放大了,小于1是缩小了,负数表示坐标翻转了。
行列式和叉乘的关系如下:
Coqui TTS
🐸(青蛙)TTS
https://github.com/coqui-ai/TTS
For the first time, tts need to download a data model. If the download fails, it will fail for the second time. We need to remove empty data model folder from path below to make it do a retry download:
/home/hgneng/.local/share/tts/
希尔贝壳中文普通话语音数据库AISHELL-3的语音时长为85小时88035句,可做为多说话人合成系统。录制过程在安静室内环境中, 使用高保真麦克风(44.1kHz,16bit)。218名来自中国不同口音区域的发言人参与录制。专业语音校对人员进行拼音和韵律标注,并通过严格质量检验,此数据库音字确率在98%以上。
Common Voice Dataset
We’re building an open source, multi-language dataset of voices that anyone can use to train speech-enabled applications.
Includes both Cantonese and Mandarin Chinese!!
抽样粤语(Chinese Hong Kong)语音数据的质量不好,录音人声音不够清晰(不是声优级别的声音),背景噪音较大,标记文件有错。另外还有个Cantonese的分类。
感觉可能用现有的TTS生成数据质量会好得多。
1. Open Visual Studio Code.
2. Go to the Extensions tab (Ctrl+Shift+X) and install the Python extension.
3. Go to File > Preferences > Settings.
4. In the left pane, search for “conda”.
5. In the right pane, search for “python.condaPath” and set the path to your Anaconda installation.
6. In the left pane, search for “conda env”.
7. In the right pane, search for “python.condaEnvFile” and set the path to your environment file.
According to https://docs.coqui.ai/en/stable/models/xtts.html , it supports Chinese.
run this to check:
tts --model_name tts_models/multilingual/multi-dataset/xtts_v2 \
--list_language_idx
When it fails download, try to set proxy (pay attention that it's "http" for https_proxy):
/var/log/journal/*
查看日志:
journalctl
journalctl -r
清理日志,仅保留180天:
sudo journalctl --vacuum-time=180d
热门内容
最新内容
- 1 day 17 hours ago
- 3 days 19 hours ago
- 6 days 19 hours ago
- 1 week 2 days ago
- 2 weeks 3 days ago
- 2 weeks 6 days ago
- 2 weeks 6 days ago
- 2 weeks 6 days ago
- 2 weeks 6 days ago
- 3 weeks ago
最新评论