AppTek Call-Center Dialogues - Chinese 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 Chinese-accented English calls, with Silero segmentation; lower is better.

Metric: Word error rate (%) on the Chinese-accented English (en_CN) 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-1.7B10.3
2Qwen3-ASR-0.6B11.7
3canary-qwen-2.5B12.1
4parakeet-tdt-0.6B-v212.6
5parakeet-tdt-0.6B-v312.9
6Phi-4 Multimodal Instruct13.3#4154
7canary-1B-v214.7
8granite-speech-3.3-8B14.8
9kyutai-stt-pytorch-stt-2.6B-en15.6
10whisper-large-v218.2
11granite-speech-3.3-2B18.8
12Whisper Large-v320.1

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-chinese-english · How It Works · Data refreshed daily, snapshot 2026-11-21.