voicescribe-whisper / UPSTREAM_SOURCE.md
Andrewsab's picture
Voice Scribe mirror whisper from FluidInference/whisper-large-v3-turbo-int4-ov-npu@2e8fe5d17cf3
9e40266 verified
# Voice Scribe Model Mirror
This repository is a Voice Scribe distribution mirror. The model artifacts are
copied from the upstream repository and the source revision below is pinned.
| Field | Value |
| --- | --- |
| Layout key | `whisper` |
| Target directory in installer | `whisper-large-v3-turbo-int4-ov` |
| Upstream repo | `FluidInference/whisper-large-v3-turbo-int4-ov-npu` |
| Upstream revision | `2e8fe5d17cf32c8b997941667285bfec0cc69d4a` |
| Upstream resolved SHA | `2e8fe5d17cf32c8b997941667285bfec0cc69d4a` |
| Mirror created | `2026-04-23T22:21:37Z` |
| Description | Whisper large-v3-turbo Intel/OpenVINO NPU layout. |
| License metadata | `{"license": "apache-2.0", "license_files": [], "license_tags": ["license:apache-2.0"]}` |
## Installer Contract
This mirror corresponds to `parakeet/installer/wrapper/model_catalog.py`.
Required files for installer validation:
```json
[
"config.json",
"generation_config.json",
"preprocessor_config.json",
"tokenizer.json",
"tokenizer_config.json",
"special_tokens_map.json",
"added_tokens.json",
"merges.txt",
"vocab.json",
"normalizer.json",
"openvino_encoder_model.xml",
"openvino_encoder_model.bin",
"openvino_decoder_model.xml",
"openvino_decoder_model.bin",
"openvino_decoder_with_past_model.xml",
"openvino_decoder_with_past_model.bin",
"openvino_tokenizer.xml",
"openvino_tokenizer.bin",
"openvino_detokenizer.xml",
"openvino_detokenizer.bin"
]
```
Allowed installer subset patterns:
```json
[]
```
## Redistribution Note
Do not make this repository public unless the upstream license and model card
allow redistribution for the intended use. Private mirrors are for operational
distribution convenience and reproducible installs.