|
Download README.md from Psycheros/vad-bert: direct link, hf CLI and curl.
- Browser
- Download file 1.99 kB
-
https://huggingface.co/Psycheros/vad-bert/resolve/main/README.md
- Command line
-
hf download hf://Psycheros/vad-bert/README.md
-
curl -L -o README.md https://huggingface.co/Psycheros/vad-bert/resolve/main/README.md
1.99 kB
metadata
language: en
tags:
- vad
- emotion
- bert
- onnx
license: mit
base_model:
- RobroKools/vad-bert
datasets:
- reallycarlaost/emobank
vad-bert (ONNX + int8, Psycheros builds)
ONNX exports of RobroKools/vad-bert (BERT-base fine-tuned on EmoBank for Valence/Arousal/Dominance regression), prepared for transformers.js-style in-process inference — no PyTorch, no server.
Two variants, identical behavior:
| variant | size | notes |
|---|---|---|
int8/ |
~110MB | dynamic int8 quantization; ~2–2.6× faster on CPU, ~0.02 delta drift |
fp32/ |
~438MB | bit-exact conversion of the original weights |
Each folder is a standalone transformers.js layout: tokenizer/config at the
root, onnx/model.onnx single-file. In both variants the model file is named
onnx/model.onnx regardless of precision.
What was done to the weights
fp32/— ONNX export of the originalpytorch_model.binvia optimum (format conversion only; weights unchanged, verified output-identical).int8/— dynamic int8 quantization of that export via onnxruntime (quantize_dynamic, QInt8).- Tokenizer and config files are re-serialized by the export tooling —
semantically identical (same tokens, same ids, same model config), but the
JSON shape differs from the original repo's (newer transformers serializes
special tokens in expanded form).
tokenizer.jsonandvocab.txtare byte-identical to the original.
Credits & license
- Original model: RobroKools/vad-bert — MIT
- Base model: google-bert/bert-base-uncased — Apache 2.0
- Training data: EmoBank (via reallycarlaost/emobank)
This repository is distributed under the same MIT license as the original; see LICENSE and the original's license above.