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

Metric: Word error rate (%) on the Mexican-accented English (en_MX) 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-1.7B9.3
2Qwen3-ASR-0.6B10.3
3canary-qwen-2.5B10.6
4Phi-4 Multimodal Instruct10.9#4154
5parakeet-tdt-0.6B-v310.9
6parakeet-tdt-0.6B-v210.9
7canary-1B-v212.2
8granite-speech-3.3-8B12.6
9kyutai-stt-pytorch-stt-2.6B-en13.2
10granite-speech-3.3-2B13.2
11whisper-large-v214.3
12Whisper Large-v318.4

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