Test
Whisper Medium on English YouTube Audio — March 31, 2026 Benchmark (WER, CER, RTF)
A reproducible ASR benchmark on ~17.3 minutes of English YouTube audio using Whisper medium, with strict and relaxed WER/CER plus RTF from evaluate-vtt-metrics.js.
Whisper Medium on English YouTube Audio — March 30, 2026 Benchmark (WER, CER, RTF)
A reproducible ASR benchmark on ~22.7 minutes of English YouTube audio using Whisper medium, with strict and relaxed WER/CER plus RTF from evaluate-vtt-metrics.js.
Eric King
Whisper Large v3 Turbo on English YouTube Audio — March 29, 2026 Benchmark (WER, CER, RTF)
A reproducible ASR evaluation on ~18 minutes of English audio from a YouTube source using Whisper large-v3-turbo, with WER/CER/RTF versus the video’s provided captions (reference VTT) and neutral error-pattern analysis.
Eric King
Whisper Large v3 Turbo on an English Interview — March 28, 2026 Benchmark (WER, CER, RTF)
A reproducible ASR evaluation on ~8.5 minutes of English interview audio using Whisper large-v3-turbo, with WER/CER/RTF versus the source video’s provided captions (reference VTT) and a neutral error-pattern analysis.
Eric King
I Tested AI Transcription on an English Interview — February 26, 2026 Results (Whisper BASE, ~11‑Minute Audio)
A reproducible Whisper BASE benchmark on an 11‑minute English interview, with detailed WER, CER, RTF metrics, error analysis and practical guidance for real‑world transcription.
Eric King
Try It Free Now
Try our AI audio and video service! You can not only enjoy high-precision speech-to-text transcription, multilingual translation, and intelligent speaker diarization, but also realize automatic video subtitle generation, intelligent audio and video content editing, and synchronized audio-visual analysis. It covers all scenarios such as meeting recordings, short video creation, and podcast production—start your free trial now!