AirCaps A5S Async v1 Benchmark - LibriSpeech test-clean OpenASR clips - cpWER: leaderboard

AirCaps A5S Async v1 Benchmark - LibriSpeech test-clean OpenASR clips - cpWER — AirCaps A5S Async v1 author comparison, November2026. Same 16kHz mono16bit WAV full recordings and native API defaults, with only exact model, language and diarization set. English language is en; Mandarin datasets use their native language. Meta switches from file to realtime above10min with same model/mode. Other documented request limits use fewest equal chunks, two-minute overlap and reference-blind stitching. Failed recordings are empty transcripts/all deletions. References and hypotheses receive OpenASR normalization plus ellipsis removal and split-numeral joining, per speaker runs, then MeetEval minimum-permutation error. Nvidia is BF16 self-hosted1xH100, temperature0,top_p1,seed0,reasoningoff and its published benchmark prompt; NVIDIA generation-loop guardrail retained. Model runs and native request settings are attached. AirCaps accuracy runNovember6; peersNovember1–2. This campaign is distinct from VoiceArena or another evaluator using the same corpus. Single-speaker clips from OpenASR short-form sets; author code computes cpWER and explicitly states it equals WER for these sets. Metric: cpWER (%). Source: https://github.com/aircaps/a5s-async-v1-benchmark

Metric: cpWER (%). Source: github.com. Saturation forecast: Rough model projection: around 2026. 9 models tracked. Updated 16 Nov 2026.

Top models

#ModelScoreOverall rank
1Nemotron 3.5 Transcribe1.44
2AirCaps A5S Async v11.58
3AssemblyAI Universal-3.5 Pro1.62
4Scribe v21.82
5MAI-Transcribe-21.91
6Grok Voice Transcribe 2.02.11
7Gemini 3.5 Transcribe2.3
8Deepgram Nova 32.57
9Muse Voice Transcribe 1.05.15

Interactive version: theaggregate.ai/benchmark?slug=aircaps-a5s-async-v1-benchmark-librispeech-test-clean-openasr-clips-cpwer · How It Works · Data refreshed daily, snapshot 2026-11-16.