Tested whisper.cpp vs faster-whisper on LibriSpeech: 4.71% vs 4.42% WER. Here's exactly where quantization drops accuracy and which to deploy on edge.

Read the full article: Whisper.cpp vs Faster-Whisper: WER Accuracy Test on LibriSpeech

You're receiving this because you subscribed to TildAlice newsletter. | #whisper.cpp, #faster-whisper, #LibriSpeech WER, #edge ASR, #speech recognition benchmarks