Benchmarks

We present throughput comparisons between easytranscriber and WhisperX. See the github repository for details, and inference code.

In general, easytranscriber achieves a greater speedup on hardware with slower single-core CPU performance. The CPU bottlenecks performance in WhisperX due to the library’s use of sequential data loading, along with its CPU-based single-threaded forced alignment implementation.

easytranscriber vs WhisperX

All easytranscriber benchmarks were run using the ctranslate2 backend for transcription.

• PyTorch version: 2.8.0
• CUDA: 12.8
• WhisperX version: 3.7.6
• Model: KBLab/kb-whisper-large
• Language: Swedish (sv)