Speech recognition to text

This is an offline native speech recognition tool based on the fast-whisper open source model. Human speech can be recognized from audio or video and converted into text. Support output formats: 📄 JSON ˇSRT subtitles ˇ Pure text️ This project has been adapted to the lazy cat online disk, and you can directly select files in the online disk to convert voice to text. 📁Model storage path: Lazy Cat Network Disk/stt/model If the model cannot be downloaded automatically, you can enter the project, click "Download Model"ˇin the upper right corner, and follow the tutorial to place the model in the corresponding folder. The base model is recommended by default.