Our great sponsors
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
Hey, sorry for no answering sooner. I feel I should create a proper guide for this, but in short I use Whisper (from the creators of ChatGPT https://github.com/openai/whisper). Recently, SubtitleEdit (similar to Aegisubs, better in my opinion) added this function to the program (https://github.com/SubtitleEdit/subtitleedit/releases); you just add a video or audio, go to Video>Audio to Text (Whisper) and it does the job. It can do straight to Korean or do some AI translation too.
Hey, sorry for no answering sooner. I feel I should create a proper guide for this, but in short I use Whisper (from the creators of ChatGPT https://github.com/openai/whisper). Recently, SubtitleEdit (similar to Aegisubs, better in my opinion) added this function to the program (https://github.com/SubtitleEdit/subtitleedit/releases); you just add a video or audio, go to Video>Audio to Text (Whisper) and it does the job. It can do straight to Korean or do some AI translation too.
This requires a GPU, the better it is, the faster it does it (selecting a "Big" model when prompted). But there's one for CPUs (https://github.com/ggerganov/whisper.cpp/); downside is you need to use a command line for this and convert it to wav 16bit 16kHz, they tell you how on their github page.