Benchmark Almanac

UrduSER

whisper-large 60% tops its leaderboard
Not in model cards

Models identify emotions in Urdu dialogue from Pakistani television. The corpus contains 3,500 excerpts from ten actors across seven emotion categories.

KuralHub publishes held-out results for 11 speech models under UrduSER. The first deposit used the name UrSEC.

Released
December 2024
Kind
Audio understanding and voice
Level
Everyday
Scored
Checked automatically
Answers
Prediction
Tasks
All public
Measures
Capability
Language
Urdu
In and out
Audio → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Audio and speech
11
Entries on its own leaderboard, 0 models we track

whisper-large tops the leaderboard with 60%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

  1. 1 whisper-large 60%
  2. 2 whisper-small 56%
  3. 3 wavlm-base-plus 52%
  4. 4 hubert-base-ls960 51%
  5. 5 wav2vec2-base 46%
  6. 6 wavlm-large 45%
  7. 7 hubert-large-ls960-ft 32%
  8. 8 wav2vec2-xls-r-300m 28%
  9. 9 wav2vec2-xls-r-1b 26%
  10. 10 wav2vec2-large-960h 24%
  11. 11 wav2vec2-large-lv60 23%

Source: Official UrduSER leaderboard

#EntryScoreSettingDateLinkSource
1 whisper-large 60% github.com Official leaderboard
2 whisper-small 56% github.com Official leaderboard
3 wavlm-base-plus 52% github.com Official leaderboard
4 hubert-base-ls960 51% github.com Official leaderboard
5 wav2vec2-base 46% github.com Official leaderboard
6 wavlm-large 45% github.com Official leaderboard
7 hubert-large-ls960-ft 32% github.com Official leaderboard
8 wav2vec2-xls-r-300m 28% github.com Official leaderboard
9 wav2vec2-xls-r-1b 26% github.com Official leaderboard
10 wav2vec2-large-960h 24% github.com Official leaderboard
11 wav2vec2-large-lv60 23% github.com Official leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Audio and video

All 695 in Audio and video
  • Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
  • LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
  • MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
  • MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
  • FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better. Phi-4-multimodal 4.00%
  • VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (11 entries).
  • Pass Models scored 11 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on aaivu.github.io: 11 entries at the last read, none a model we track.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check