← Speech to text (English) libraries · Reader board

faster-whisper 1.2.1 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.

Note: With PyAV 18.1.0: faster-whisper 1.2.1 (the latest release) fails on every file with PyAV 19 (fixed on its main branch, not released yet). why

🔴 Fails where another library reads text: none

🟡 Empty where another library reads text: none

⚔️ Compare: faster-whisper vs Whisper · faster-whisper vs whisper.cpp · faster-whisper vs Vosk · Parakeet vs faster-whisper · Moonshine vs faster-whisper

Changes between versions

Only one version tested so far. The next PyPI release is tested automatically.

Badge

For a README: badge

[![Reader board](https://img.shields.io/endpoint?url=https://prometheus-maker.github.io/reader-board/badges/speech-faster-whisper.json)](https://prometheus-maker.github.io/reader-board/speech-faster-whisper.html)

Slowest files

earnings-calls/457_12_45.wav7.538 s, 566 MB
ami-close-mic/AMI_EN2002a_H01_FEO070_0106053_0106854.wav6.382 s, 470 MB
earnings-calls/379_9_78.wav2.372 s, 523 MB
fleurs/8398257681626621326.wav1.001 s, 567 MB
ami-close-mic/AMI_EN2002a_H00_MEE073_0030336_0030633.wav0.997 s, 361 MB
librispeech-clean/1221-135767-0003.wav0.986 s, 568 MB
librispeech-clean/8224-274384-0010.wav0.879 s, 568 MB
librispeech-other/5484-24317-0027.wav0.872 s, 568 MB
earnings-calls/88_5_38.wav0.838 s, 566 MB
librispeech-clean/5683-32866-0019.wav0.835 s, 568 MB

Recipe: board/targets.py. Run: 2026-11-06T19:40:18Z, Python 3.13.18, Linux x86_64, 4 CPUs (log). Installed: PyYAML==6.0.3, RapidFuzz==3.14.6, anyio==4.16.0, av==18.1.0, click==8.5.1, ctranslate2==4.8.5, faster-whisper==1.2.1, filelock==4.2.9, flatbuffers==25.12.19, fsspec==2026.9.0, h11==0.16.0, hf-xet==1.8.0, httpcore2==2.16.0, httpx2==2.16.0, huggingface_hub==2.4.0, idna==3.20, indic_numtowords==1.1.0, more-itertools==11.2.1, numpy==2.5.4, onnxruntime==1.31.1, packaging==26.3, protobuf==7.36.2, regex==2026.9.29, text2num==3.1.0, tokenizers==0.23.3, tqdm==4.70.1, truststore==0.10.5, typing_extensions==4.16.0, whisper_normalizer==1.0.0