← Speech to text (English) libraries · Reader board
Whisper 20250625 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 · Vosk vs Whisper · whisper.cpp vs Whisper · Parakeet 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.html)Slowest files
| ami-close-mic/AMI_EN2002a_H00_MEE073_0030336_0030633.wav | 3.288 s, 844 MB |
| librispeech-other/7902-96592-0048.wav | 2.877 s, 880 MB |
| librispeech-clean/5683-32866-0019.wav | 2.311 s, 879 MB |
| librispeech-other/5484-24317-0027.wav | 2.285 s, 879 MB |
| earnings-calls/328_1_0.wav | 2.112 s, 879 MB |
| librispeech-clean/1089-134691-0009.wav | 2.094 s, 879 MB |
| earnings-calls/735_10_43.wav | 2.066 s, 879 MB |
| fleurs/9327483361259434782.wav | 1.968 s, 879 MB |
| librispeech-clean/1221-135767-0003.wav | 1.963 s, 879 MB |
| ami-close-mic/AMI_EN2002b_H03_MEE073_0176882_0177179.wav | 1.954 s, 854 MB |
Recipe: board/targets.py. Run: 2026-11-06T19:42:38Z, Python 3.13.18, Linux x86_64, 4 CPUs (log). Installed: Jinja2==3.1.6, MarkupSafe==3.0.4, RapidFuzz==3.14.6, certifi==2026.10.23, charset-normalizer==3.5.2, filelock==4.2.9, fsspec==2026.9.0, idna==3.20, indic_numtowords==1.1.0, llvmlite==0.50.0, more-itertools==11.2.1, mpmath==1.3.0, networkx==3.7, numba==0.68.1, numpy==2.5.4, openai-whisper==20250625, regex==2026.9.29, requests==2.34.2, sympy==1.14.0, text2num==3.1.0, tiktoken==0.14.0, torch==2.15.0+cpu, tqdm==4.70.1, triton==3.9.0, typing_extensions==4.16.0, urllib3==2.8.0, whisper_normalizer==1.0.0