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

Dimensions overall score 7.0

• This research benchmarks multilingual speech models on Pashto, identifying critical failures and proposing a path for improved performance on under-resourced languages. 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.problem 35%
  Evidencepartial

  This research benchmarks multilingual speech models on Pashto, identifying critical failures and proposing a path for improved performance on under-resourced languages. 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.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

• 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.method 35%
  Evidencepartial

  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.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

• ScienceToStartup currently rates this 7.0/10 on the public viability pass. 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. Code availability is flagged in the production record; the public repository link still needs proof alignment.result 35%
  Evidencepartial

  ScienceToStartup currently rates this 7.0/10 on the public viability pass. 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. Code availability is flagged in the production record; the public repository link still needs proof alignment.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

• Multilingual Speech AI moved forward this cycle; last verified April 2026. Public score 7.0/10. Production flags indicate code availability.why now 35%
  Evidencepartial

  Multilingual Speech AI moved forward this cycle; last verified April 2026. Public score 7.0/10. Production flags indicate code availability.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

Competitive landscape

This research benchmarks multilingual speech models on Pashto, identifying critical failures and proposing a path for improved performance on under-resourced languages.