Productopenai/whisper / 参考实现
openai/whisper
The original PyTorch reference implementation of Whisper. It is the most feature-complete version but also the slowest and heaviest in dependencies, making it suitable for scenarios that require its unique capabilities.
Timeline (last 90 days)
Oct 15
There are three viable paths for self-hosting Whisper: whisper.cpp (a C/C++ port, with no Python dependency), faster-whisper (based on CTranslate2, several times faster), and the reference implementation openai/whisper (the original PyTorch version).
Unverified50%