Skip to content

docs(js/ort-whisper): add olive installation instructions and fix broken Olive link #587

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Reginald Alfret V (reginaldalfret) wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs(js/ort-whisper): add olive installation instructions and fix broken Olive link #587

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 11 additions & 3 deletions js/ort-whisper/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,16 +21,24 @@ this generates the bundle file `./dist/bundle.min.js`
### Create an ONNX Model
To create an optimized end-to-end ONNX model from the original OpenAI Whisper model, follow these steps:

1. Goto: https://github.com/microsoft/Olive/tree/main/examples/whisper and follow the instructions.
1. Install Olive:
```sh
pip install olive-ai[cpu]
```

2. Go to the Olive Whisper example at https://github.com/microsoft/Olive/tree/v0.6.0/examples/whisper and install the example requirements:
```sh
pip install -r requirements.txt
```

2. Run the following commands
3. Run the following Olive commands to optimize the Whisper model:
```sh
python prepare_whisper_configs.py --model_name openai/whisper-tiny.en --no_audio_decoder
python -m olive.workflows.run --config whisper_cpu_int8.json --setup
python -m olive.workflows.run --config whisper_cpu_int8.json
```

3. Move the resulting model from models/whisper_cpu_int8_0_model.onnx to the same directory as this code.
4. Move the resulting model from `models/whisper_cpu_int8_0_model.onnx` into `js/ort-whisper/`.

### Start a web server
Use NPM package `light-server` to serve the current folder at http://localhost:8888/.
Expand Down
Loading