← Speech to text (English) libraries · Reader board
whisper.cpp 1.5.1 on Speech to text (English)
130 files: text from 130, empty 0, errors 0, hangs 0, crashes 0. 130 files give text to at least one library.
🔴 Fails where another library reads text: none
🟡 Empty where another library reads text: none
⚔️ Compare: faster-whisper vs whisper.cpp · whisper.cpp vs Whisper
Changes between versions
Only one version tested so far. The next PyPI release is tested automatically.
Badge
For a README:
[](https://prometheus-maker.github.io/reader-board/speech-whisper-cpp.html)Slowest files
| earnings-calls/49_13_72.wav | 1.67 s, 342 MB |
| librispeech-other/5484-24317-0027.wav | 1.589 s, 342 MB |
| librispeech-clean/5683-32866-0019.wav | 1.572 s, 342 MB |
| librispeech-clean/1089-134691-0009.wav | 1.545 s, 342 MB |
| librispeech-clean/1221-135767-0003.wav | 1.507 s, 342 MB |
| fleurs/8398257681626621326.wav | 1.503 s, 342 MB |
| earnings-calls/735_10_43.wav | 1.484 s, 342 MB |
| ami-close-mic/AMI_EN2002a_H00_MEE073_0030336_0030633.wav | 1.474 s, 295 MB |
| ami-far-field/AMI_EN2002c_sdm_MEE071_0048700_0048948.wav | 1.449 s, 339 MB |
| librispeech-clean/1221-135766-0003.wav | 1.401 s, 342 MB |
Recipe: board/targets.py. Run: 2026-11-06T19:41:45Z, Python 3.13.18, Linux x86_64, 4 CPUs (log). Installed: RapidFuzz==3.14.6, certifi==2026.10.23, charset-normalizer==3.5.2, idna==3.20, indic_numtowords==1.1.0, more-itertools==11.2.1, numpy==2.5.4, platformdirs==4.14.5, pywhispercpp==1.5.1, regex==2026.9.29, requests==2.34.2, text2num==3.1.0, tqdm==4.70.1, urllib3==2.8.0, whisper_normalizer==1.0.0