Skip to content

Benchmark

Pashto ASR FLEURS ps_af script La (zero-shot)

Scores are percentages.

Models measured
7
Scores recorded
7
Sources
1
IQ weight
No weight published

Score distribution

25.4%
Mean
9.4%
Median
29.7%
Std dev
0%
10th percentile
56.2%
90th percentile
0%
Min
0%81.6%
The band covers the middle 80% of scores. The line marks the median.

Results

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

ModelScore
Whisper Basetable: III, dataset: FLEURS ps_af, metric: script La, protocol: zero-shot· Pashto ASR paper data56.2%
Whisper Large v2table: III, dataset: FLEURS ps_af, metric: script La, protocol: zero-shot· Pashto ASR paper data28.1%
Whisper Large V3table: III, dataset: FLEURS ps_af, metric: script La, protocol: zero-shot· Pashto ASR paper data0%
Whisper Large V3 Turbotable: III, dataset: FLEURS ps_af, metric: script La, protocol: zero-shot· Pashto ASR paper data0%
Whisper Mediumtable: III, dataset: FLEURS ps_af, metric: script La, protocol: zero-shot· Pashto ASR paper data9.4%
Whisper Smalltable: III, dataset: FLEURS ps_af, metric: script La, protocol: zero-shot· Pashto ASR paper data2.3%
Whisper Tinytable: III, dataset: FLEURS ps_af, metric: script La, protocol: zero-shot· Pashto ASR paper data81.6%

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)