Corpus of Multilingual Code-switched Soap Opera Speech
Models transcribe South African television dialogue in which speakers switch between English and four Southern African languages.
Reitmaier and colleagues compared an XLSR-53 system and a hybrid recognizer on the soap opera test set using word error rate.
- Made by
- Stellenbosch University
- Released
- May 2018
- Kind
- Speech recognition and translation
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- Many languages
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Audio and speech, Many languages
whisper-medium, same data, fixed recipe tops the leaderboard with 26%
Best score per entry from isiXhosa Speech AI’s 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 whisper-medium, same data, fixed recipe R-0035 26%
- 2 whisper-medium, + Swivuriso 245 h R-0029 28.1%
- 3 whisper-medium, + Swivuriso 147 h R-0019 29.3%
- 4 whisper-small, + Swivuriso 245 h R-0027 32.8%
- 5 whisper-medium, NCHLT + FLEURS R-0012 38.4%
- 6 whisper-small, NCHLT + FLEURS R-0007 42.1%
Source: IsiXhosa Speech AI’s leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | whisper-medium, same data, fixed recipe | 26% | R-0035 | github.com | Official leaderboard | |
| 2 | whisper-medium, + Swivuriso 245 h | 28.1% | R-0029 | github.com | Official leaderboard | |
| 3 | whisper-medium, + Swivuriso 147 h | 29.3% | R-0019 | github.com | Official leaderboard | |
| 4 | whisper-small, + Swivuriso 245 h | 32.8% | R-0027 | github.com | Official leaderboard | |
| 5 | whisper-medium, NCHLT + FLEURS | 38.4% | R-0012 | github.com | Official leaderboard | |
| 6 | whisper-small, NCHLT + FLEURS | 42.1% | R-0007 | 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
- 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 (6 entries).
- Pass Models scored 6 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
- Pass Importer We read the board on isiXhosa Speech AI: 6 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.