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_nvidia |
| Target directory in installer | whisper-large-v3-turbo-onnx |
| Upstream repo | onnx-community/whisper-large-v3-turbo |
| Upstream revision | 360ebcde2559d60bb474678be3c1de9ef347d01a |
| Upstream resolved SHA | 360ebcde2559d60bb474678be3c1de9ef347d01a |
| Mirror created | 2026-04-23T22:35:10Z |
| Description | Whisper large-v3-turbo ONNX NVIDIA layout. |
| License metadata | {"license": null, "license_files": [], "license_tags": []} |
Installer Contract
This mirror corresponds to parakeet/installer/wrapper/model_catalog.py.
Required files for installer validation:
[
"config.json",
"generation_config.json",
"preprocessor_config.json",
"tokenizer.json",
"tokenizer_config.json",
"special_tokens_map.json",
"added_tokens.json",
"merges.txt",
"normalizer.json",
"onnx/encoder_model.onnx",
"onnx/encoder_model.onnx_data",
"onnx/decoder_model.onnx",
"onnx/decoder_with_past_model.onnx",
"onnx/encoder_model_fp16.onnx",
"onnx/decoder_model_fp16.onnx",
"onnx/decoder_with_past_model_fp16.onnx"
]
Allowed installer subset patterns:
[
"config.json",
"generation_config.json",
"preprocessor_config.json",
"tokenizer.json",
"tokenizer_config.json",
"special_tokens_map.json",
"added_tokens.json",
"merges.txt",
"normalizer.json",
"onnx/encoder_model.onnx",
"onnx/encoder_model.onnx_data",
"onnx/decoder_model.onnx",
"onnx/decoder_with_past_model.onnx",
"onnx/encoder_model_fp16.onnx",
"onnx/decoder_model_fp16.onnx",
"onnx/decoder_with_past_model_fp16.onnx"
]
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.