# Benchmarking Multilingual Speech Models on Pashto: Zero-Shot ASR, Script Failure, and Cross-Domain Evaluation

arXiv: https://arxiv.org/abs/2604.04598 · HTML: https://mlsanity.com/paper/2604.04598/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Seamless: Multilingual Expressive and Streaming Speech Translation](https://mlsanity.com/paper/2312.05187/) (2023)
- [VoxLingua107: a Dataset for Spoken Language Recognition](https://mlsanity.com/paper/2011.12998/) (2020)
- [Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages](https://mlsanity.com/paper/2511.09690/) (2025)
- [Advocating Character Error Rate for Multilingual ASR Evaluation](https://mlsanity.com/paper/2410.07400/) (2024)
- [What is lost in Normalization? Exploring Pitfalls in Multilingual ASR Model Evaluations](https://mlsanity.com/paper/2409.02449/) (2024)
- [WER We Stand: Benchmarking Urdu ASR Models](https://mlsanity.com/paper/2409.11252/) (2024)

## Built on by (most cited first, 2 of 2)

- [PashtoTTS-Bench: automated screening for low-resource non-Latin-script text-to-speech](https://mlsanity.com/paper/2605.26978/) (2026)
- [Fine-tuning Whisper for Pashto ASR: strategies and scale](https://mlsanity.com/paper/2604.06507/) (2026)

## Abstract (arXiv)

Pashto is spoken by approximately 60--80 million people but has no published benchmarks for multilingual automatic speech recognition (ASR) on any shared public test set. This paper reports the first reproducible multi-model evaluation on public Pashto data, covering zero-shot ASR, script-level failure, and cross-domain evaluation of fine-tuned models. For zero-shot ASR, ten models (all seven Whisper sizes, MMS-1B, SeamlessM4T-v2-large, and OmniASR-CTC-300M) are evaluated on the FLEURS Pashto test set and a filtered Common Voice~24 subset; zero-shot Whisper WER ranges from 90% to 297%, with the medium model collapsing to 461% on Common Voice~24 consistent with decoder looping. SeamlessM4T achieves 39.7% WER on Common Voice~24 (the best zero-shot result reported to date, as of submission); MMS-1B achieves 43.8% on FLEURS. For script failure, a language-identification audit shows that no Whisper model produces Pashto-script output in more than 0.8% of utterances, while MMS-1B, SeamlessM4T, and OmniASR each exceed 93% Pashto-script fidelity; WER alone does not reveal this failure, since a model generating Arabic-script output on Pashto audio has not achieved ASR in any interpretable sense. For cross-domain evaluation, five fine-tuned Pashto ASR models are evaluated on both test sets: published WER figures of 14% degrade to 32.5--59% on out-of-distribution sets, while one augmented model achieves 35.1% on both sets with zero cross-domain degradation. Character-class error stratification confirms that Pashto-unique phonemes (the retroflex series and lateral fricatives) account for disproportionate error mass. All evaluations cover read speech only. Five structural impediments to cumulative progress are identified and five ordered research priorities are argued.