AppTek Call-Center Dialogues - Singaporean English: leaderboard

AppTek Call-Center Dialogues (2026) is a long-form English speech recognition test set of spontaneous role-played call-center conversations in 14 accents, recorded for evaluation only. This board is the word error rate in percent on the Singaporean-accented English calls, with Silero segmentation; lower is better.

Metric: Word error rate (%) on the Singaporean-accented English (en_SG) calls of AppTek Call-Center Dialogues (128.6 hours of spontaneous role-played English call-center conversations, 14 accents), default inference settings, scored per session after Open ASR Leaderboard text normalization, audio segmented with the Silero VAD; lower is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen3-ASR-1.7B10.9
2canary-qwen-2.5B12.1
3parakeet-tdt-0.6B-v312.4
4Qwen3-ASR-0.6B12.4
5parakeet-tdt-0.6B-v212.4
6Phi-4 Multimodal Instruct14.3#4154
7canary-1B-v214.9
8whisper-large-v215.9
9kyutai-stt-pytorch-stt-2.6B-en16.5
10Whisper Large-v318
11granite-speech-3.3-8B18.8
12granite-speech-3.3-2B19.1

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=apptek-call-center-dialogues-singaporean-english · How It Works · Data refreshed daily, snapshot 2026-11-21.