Open Pashto language technology catalog

Find useful Pashto resources without digging through noise.

Browse curated datasets, papers, models, benchmarks, and tools for speech, text, OCR, NLP, and machine translation work.

Open resource search Browse papers

Choose a Starting Point

Focused pages help you jump directly into the kind of Pashto work you are doing.

Filter datasets, models, tools, benchmarks, code, and projects by task, source, review status, and keyword.

Datasets Models Tools

Search resources

Explore Pashto research papers with task filters for ASR, OCR, machine translation, NLP, and speech work.

ASR MT OCR

Open papers

Start with public Pashto datasets, corpus links, speech data, text data, and evaluation resources.

Speech Text MT

View datasets

Find automatic speech recognition datasets, models, benchmarks, and papers for Pashto speech.

Speech Benchmarks

ASR page

Find text-to-speech papers, datasets, models, and training references for Pashto voice systems.

Voice Speech synthesis

TTS page

Use the catalog guide and contribution notes to add useful resources, improve metadata, or remove dead and low-value links.

Quality checks Metadata Automation

Read catalog guide

Use search first when you need a resource quickly. Use the topic pages when you are planning a focused ASR, TTS, dataset, OCR, NLP, or MT workflow.

Contribute

Task filters surface resource groups such as ASR, TTS, OCR, NLP, and machine translation.

Every result keeps the original URL visible so you can verify the project, paper, dataset, or model card yourself.

Curated and checked entries are highlighted, while the automation filters out empty, deleted, and placeholder resources.