Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/Nachimak28/LAI-voice-search-openai-whisper-demo
A ⚡️ Lightning.ai ⚡️ app demo for Voice based web search using OpenAI's Whisper and DuckDuckGo
https://github.com/Nachimak28/LAI-voice-search-openai-whisper-demo
openai speech-to-text websearch whisper
Last synced: about 2 months ago
JSON representation
A ⚡️ Lightning.ai ⚡️ app demo for Voice based web search using OpenAI's Whisper and DuckDuckGo
- Host: GitHub
- URL: https://github.com/Nachimak28/LAI-voice-search-openai-whisper-demo
- Owner: Nachimak28
- License: apache-2.0
- Created: 2022-09-22T18:02:35.000Z (almost 2 years ago)
- Default Branch: master
- Last Pushed: 2022-10-25T14:29:01.000Z (almost 2 years ago)
- Last Synced: 2023-02-28T16:27:33.001Z (over 1 year ago)
- Topics: openai, speech-to-text, websearch, whisper
- Language: Python
- Homepage:
- Size: 2.1 MB
- Stars: 21
- Watchers: 3
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Speech Search Engine with Whisper
[][#app-gallery]
[#app-gallery]: https://01gfax73s2tn315zme310fkh4z.litng-ai-03.litng.ai/view/home
This app is a simulation of a Voice search feature provided by search engines like Google, DuckDuckGo using OpenAI's [Whisper](https://openai.com/blog/whisper/) model.
This ⚡ [Lightning app](lightning.ai) ⚡ was generated automatically with:
```bash
lightning init app LAI_voice_search_openai_whisper_demo
```
## Sample output
## To run LAI_voice_search_openai_whisper_demo
Prerequisites
* Create a conda/venv environment
We use conda here but you can use whichever tool you're comfortable with
```bash
conda create --yes --name oaiwhisper python=3.8
conda activate oaiwhisper
```
* Install FFMPEG
FFMPEG is necessary for the audio processing
- For Windows: Follow [these steps](https://www.wikihow.com/Install-FFmpeg-on-Windows)
- For Ubuntu/Debian:
```bash
sudo apt-get update
sudo apt-get install -y ffmpeg
```
* Install packages
```bash
pip install -r requirements.txt
```
* Install app
First, install LAI_voice_search_openai_whisper_demo (warning: this app has not been officially approved on the lightning gallery):
```bash
lightning install app https://github.com/theUser/LAI_voice_search_openai_whisper_demo
```
* Run locally
Once the app is installed, run it locally with:
```bash
lightning run app LAI_voice_search_openai_whisper_demo/app.py
```
If the above does not work, manually setup the environment:
```
git clone https://github.com/Nachimak28/LAI-voice-search-openai-whisper-demo
cd LAI-voice-search-openai-whisper-demo
conda create --yes --name oaiwhisper python=3.8
conda activate oaiwhisper
python -m pip install -r requirements.txt
python -m pip install lightning
python -m lightning run app app.py
# to run on lightning cloud
python -m lightning run app app.py --cloud
```
Run it on the [lightning cloud](lightning.ai) with:
```bash
lightning run app LAI_voice_search_openai_whisper_demo/app.py --cloud
```
## to test and link
Run flake to make sure all your styling is consistent (it keeps your team from going insane)
```bash
flake8 .
```
To test, follow the README.md instructions in the tests folder.
## Steps followed to build such a feature in this minimal app
* Obtain the Speech-to-text (transcription) output using Whisper
* Use this transcribed output string as an input for [duckduckgo search](https://github.com/deedy5/duckduckgo_search)
* Once the web search results are obtained, render using HTML
## FAQ
* Why use DuckDuckGo(DDG) and not Google search?
Ans: Google has a lot of rate limiting applied and frequent searches via code lead to getting blocked resulting in status code: 429 - Too many requests. Apparently DDG does not have super strict rate limiting.
* Why Lightning.ai ?
Ans: Provisioning the infra and deployment is automated, all one needs to do is focus on business logic. Also HF spaces are too crowded with mutiple such demos.
## TODOs
- [x] Update code to accept microphone input as soon as Gradio bug is resolved
- [x] Write unit tests
- [x] Run given test
- [x] Add comments and prepare code for submission to Lightning Gallery