Benchmark
Pashto ASR FLEURS ps_af WER (zero-shot)
Scores are percentages. Lower is better.
- Models measured
- 7
- Scores recorded
- 7
- Sources
- 1
- IQ weight
- 1.11
Score distribution
- 142.5%
- Mean
- 100.6%
- Median
- 73.3%
- Std dev
- 91.8%
- 10th percentile
- 204.6%
- 90th percentile
- 89.8%
- Min
This benchmark has a weight of 1.11 for speech models, measured over 7 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Whisper Large V3table: II, dataset: FLEURS ps_af, metric: WER, protocol: zero-shot· Pashto ASR paper data | 89.8% |
| 2 | Whisper Large V3 Turbotable: II, dataset: FLEURS ps_af, metric: WER, protocol: zero-shot· Pashto ASR paper data | 91.8% |
| 3 | Whisper Large v2table: II, dataset: FLEURS ps_af, metric: WER, protocol: zero-shot· Pashto ASR paper data | 95.7% |
| 4 | Whisper Smalltable: II, dataset: FLEURS ps_af, metric: WER, protocol: zero-shot· Pashto ASR paper data | 100.6% |
| 5 | Whisper Basetable: II, dataset: FLEURS ps_af, metric: WER, protocol: zero-shot· Pashto ASR paper data | 118.2% |
| 6 | Whisper Mediumtable: II, dataset: FLEURS ps_af, metric: WER, protocol: zero-shot· Pashto ASR paper data | 204.6% |
| 7 | Whisper Tinytable: II, dataset: FLEURS ps_af, metric: WER, protocol: zero-shot· Pashto ASR paper data | 297% |
Data credits: Hanif Rahman. Benchmarking Multilingual Speech Models on Pashto: Zero-Shot ASR, Script Failure, and Cross-Domain Evaluation, arXiv:2604.04598v1. Numeric/protocol extract from Tables II, III, V and VI; CC BY 4.0 article grant verified. (licence)