Vosk is an offline open source speech recognition toolkit. It enables speech recognition for 20+ languages and dialects - English, Indian English, German, French, Spanish, Portuguese, Chinese, Russian, Turkish, Vietnamese, Italian, Dutch, Catalan, Arabic, Greek, Farsi, Filipino, Ukrainian, Kazakh, Swedish, Japanese, Esperanto, Hindi, Czech, Polish. More to come.
Today I tested this Python package with a video that contains sound content
in the Chinese language
I created a simple interface where you can test other videos on youtube and where you can select the language and start time and duration for the detection sequence with the python vosk package.
I used the python youtube_dl package to take portions of wav sound from a youtube video.
I haven't done tests on other videos but it should work.
You can find it on this colab notebook.