https://github.com/edgeimpulse/example-transform-whisper-keywords
https://github.com/edgeimpulse/example-transform-whisper-keywords
Last synced: about 2 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/edgeimpulse/example-transform-whisper-keywords
- Owner: edgeimpulse
- License: bsd-3-clause-clear
- Created: 2024-03-14T11:43:56.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-10T10:08:30.000Z (3 months ago)
- Last Synced: 2025-03-07T00:58:41.058Z (about 2 months ago)
- Language: Python
- Size: 500 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# Whisper Voice Synthesis Block for Edge Impulse
This is a transformation block that uses Whisper to generate synthetic data for your Edge Impulse project.
Input parameters:
`--phrase 'Hello'` Phrase for which to generate voice sample
`--label 'dog_with_hat'` Label to assign
`--samples 3 ` How many unique samples to generate
## How to run (Edge Impulse)
1. You'll need an OpenAI API key:
* Create an API Key: https://platform.openai.com/docs/api-reference/authentication
2. Add the API key as a secret to your Edge Impulse organization:
1. Go to your Edge Impulse organization.
2. Click **Custom blocks > Transformation**
3. Click **Add new secret**
4. Set as name: `OPENAI_API_KEY`, as value the API Key you created in step 1.
3. Create a new transformation block:
```
$ edge-impulse-blocks init
? Choose a type of block Transformation block
? Choose an option Create a new block
? Enter the name of your block Whisper Voice Generator
? Enter the description of your block Use the Whisper Voice to generate new images. Takes in --phrase, --label, --sample, --voice and --model
? What type of data does this block operate on? Standalone (runs the container, but no files / data items passed in)
? Which buckets do you want to mount into this block (will be mounted under /mnt/s3fs/BUCKET_NAME, you can change these mount points in the St
udio)?
? Would you like to download and load the example repository? no
```
4. Push the block:
```
$ edge-impulse-blocks push
```
5. Go to any project, select **Data acquisition > Data sources > Add new data source > Transformation block** and select this block.
6. After you've ran the block you'll have some new audio samples in your project 🚀
