Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: NbAiLab/nb-whisper-base
|
4 |
+
library_name: transformers.js
|
5 |
+
---
|
6 |
+
|
7 |
+
# nb-whisper-tiny-ONNX
|
8 |
+
|
9 |
+
This is a conversion of NBAiLab's [nb-whisper-base](https://huggingface.co/NbAiLab/nb-whisper-base) model to the [ONNX](https://onnx.ai) format.
|
10 |
+
|
11 |
+
|
12 |
+
This conversion allows to use the model in the browser using [🤗 Transformers.js](https://huggingface.co/docs/transformers.js/en/index).
|
13 |
+
|
14 |
+
## How to convert the model yourself
|
15 |
+
|
16 |
+
### Option 1: Use the ONXX community space
|
17 |
+
|
18 |
+
Just follow the instructions at [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
|
19 |
+
|
20 |
+
### Option 2: Local conversion
|
21 |
+
|
22 |
+
Clone 🤗 Transformers.js:
|
23 |
+
|
24 |
+
```bash
|
25 |
+
git clone https://github.com/huggingface/transformers.js.git
|
26 |
+
cd transformers.js
|
27 |
+
pip install -r scripts/requirements.txt
|
28 |
+
```
|
29 |
+
|
30 |
+
Then run:
|
31 |
+
|
32 |
+
```bash
|
33 |
+
python -m scripts.convert --quantize --model_id NbAiLab/nb-whisper-base
|
34 |
+
```
|