← Directory
software · Global
TerraMind-1.0-Tokenizer-S1RTC
Hugging Face model ibm-esa-geospatial/TerraMind-1.0-Tokenizer-S1RTC
Claim this listing
Represent TerraMind-1.0-Tokenizer-S1RTC? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.
What's in it
- Data offered docs-verified
- Sentinel-1 RTC image tokens (encode) · Sentinel-1 RTC image reconstruction from tokens (decode)
- Coverage llm-inferred
- Global
- Formats llm-inferred
- Python API via TerraTorch (tensor input and output)
- Access docs-verified
- Free and open, Apache-2.0 licence; no API key required per catalogue metadata; runs locally via TerraTorch
Useful for
- Use cases llm-inferred
- Tokenising Sentinel-1 RTC scenes as inputs to a multimodal EO model for land-cover or change-detection pre-processing · Reconstructing S-1 RTC imagery from token sequences to test radar data compression fidelity · Generating synthetic S-1 RTC image variants for data augmentation in flood or water-body mapping research
- Audience llm-inferred
- remote sensing specialists · GIS analysts · EO machine-learning engineers · hydrologists (radar flood mapping research)
Limitations
- Constraints docs-verified
- Increasing diffusion steps can add hallucinated detail to reconstructions · Tokenizer only; it is designed for use with the TerraMind model, not as a standalone product · No Inference Provider currently hosts this model, so it must be run locally
- Licence
- apache-2.0
- Authentication
- No API key required (repository README, auto-extracted; check upstream requirements)
- GitHub stars
- Unknown
- Last commit
- Unknown
- Last successful page check
- 14/10/2026
- Page health
- healthy
- Package
- Not recorded
- Verification
- Not independently verified
Provenance & evidence
Verified 2026-10-15 via HF API: exists; 3160 downloads/30d, 0 likes.
Metadata observed 14/10/2026 · research sweep: manual-2026-10-15 (Hugging Face models)