Downloads · 30 days
0
nguyendinhquoc/pho-whisper-small-onnx-int8
pho-whisper-small-onnx-int8 is a machine learning model from nguyendinhquoc. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as bsd-3-clause.
Export ONNX của vinai/PhoWhisper-small (BSD-3-Clause, VinAI Research) phục vụ thí nghiệm chạy on-device Android (bàn phím Outspoke — merged-decoder format của optimum).
Downloads · 30 days
0
Access
Public
Updated Sep 3, 2026
Repo size
1.1 GB
Likes
0
Public
Click a slice to open those files.
.onnx1.1 GB · 99%
From the Hugging Face model README
Export ONNX của vinai/PhoWhisper-small (BSD-3-Clause, VinAI Research) phục vụ thí nghiệm chạy on-device Android (bàn phím Outspoke — merged-decoder format của optimum).
| File | Quantization | Size |
|---|---|---|
onnx/encoder_model_int8.onnx | dynamic INT8 (MatMul/Gemm) | ~92 MB |
onnx/decoder_model_merged_int4.onnx | weight-only INT4 block-128 (MatMulNBits, accuracy_level=4) | ~243 MB |
tokenizer.json | — | 3.6 MB |
input_features [1, 80, 3000] → output last_hidden_state [1, 1500, 768].Exported với optimum (transformers 4.57) + onnxruntime quantization, 2026-09.