~/.local/share/rekody/models/ (override with $REKODY_MODEL_DIR). Every download is verified against a SHA-256 hash pinned in the binary; on a mismatch the file is deleted and, where a fallback source exists, the fallback is tried. Nothing unverified is left on disk.
Serving repositories
| Purpose | Primary source | Fallback |
|---|---|---|
| Streaming model | Rekody/rekody-streaming-en-0.6b-int8 | none (sole source) |
| Whisper models and Core ML encoders | Rekody/rekody-models (under whisper/) | upstream ggerganov/whisper.cpp |
Streaming model files
Thenemotron engine loads three files from models/nemotron-en-int8/, all pinned:
| File | Size | SHA-256 |
|---|---|---|
encoder.onnx | 880 MB | 83538392358e90c40592f7cf99ee65ac7dca5d144edb999ce028c372318a5753 |
decoder_joint.onnx | 11 MB | 89cae615623e41e94cc6b428708cd1a89a22965606fe7ded814b1d8e20c87368 |
tokenizer.model | SentencePiece | 07d4e5a63840a53ab2d4d106d2874768143fb3fbdd47938b3910d2da05bfb0a9 |
SHA256SUMS, so you can verify independently:
Whisper model files
whisper_model | Local file | Download |
|---|---|---|
tiny | ggml-tiny.bin | 75 MB |
small | ggml-small.bin | 250 MB |
medium | ggml-medium.bin | 750 MB |
turbo | ggml-large-v3-turbo-q5_0.bin | 574 MB |
large | ggml-large.bin (upstream ggml-large-v3.bin, saved under the engine’s expected name) | 3.1 GB |
ggml-<size>-encoder.mlmodelc.zip) is downloaded, verified against its own pinned hash, and unzipped next to the model.
All pinned hashes live in crates/rekody-core/src/onboarding.rs (EXPECTED_CHECKSUMS), with the date they were last verified.
Release binaries too
Model files are not the only artifacts verified:rekody update checks the release tarball against the SHA256SUMS file published with every GitHub release before extracting it.
Licenses
- The CLI is MIT.
- The streaming model ships under two licenses, and users must comply with both:
- The conversion work (the int8 quantization, packaging, and benchmarking) is licensed under the PolyForm Shield License 1.0.0. PolyForm Shield is a noncompete license: any use is permitted except providing a product that competes with the software or with the licensor’s products built on it.
- The base model weights remain licensed by NVIDIA Corporation under the NVIDIA Open Model License. The model repo carries the
NOTICEfile and a dated copy of the license.
- Whisper models are the whisper.cpp GGML conversions of OpenAI’s Whisper weights (MIT), mirrored byte-for-byte.