PSRB: Persian Speech Recognition Benchmark, 1-Hour Sample

PSRB (Persian Speech Recognition Benchmark) is a dataset designed to evaluate Persian Automatic Speech Recognition systems. This 1-hour sample provides a representative subset capturing various accents, speech styles, speaker demographics, and acoustic environments. The dataset was created by PartAI and was last updated on 2025-08-19.

Use Cases

• Benchmarking Persian ASR system performance based on diverse real-world conditions mentioned in the description
• Training acoustic models for Persian speech based on varied accents and speech styles
• Evaluating model robustness across different acoustic environments and speaker demographics

Strengths

• Designed to capture diverse real-world conditions including various accents, speech styles, and acoustic environments
• Represents a 1-hour sample of a larger benchmark corpus

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download
• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment

Provenance

Source

PartAI

Freshness

Last updated 2025-08-19 13:43:23