Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/FernandoLpz/SpeechRecognition
This repository contains the implementation of an Automatic Speech Recognition system in python, using a client-server architecture with Web Sockets.
https://github.com/FernandoLpz/SpeechRecognition
automatic-speech-recognition python speech-recognition speech-to-text transformers wav2vec2 websockets
Last synced: 17 days ago
JSON representation
This repository contains the implementation of an Automatic Speech Recognition system in python, using a client-server architecture with Web Sockets.
- Host: GitHub
- URL: https://github.com/FernandoLpz/SpeechRecognition
- Owner: FernandoLpz
- Created: 2022-12-10T14:38:44.000Z (almost 2 years ago)
- Default Branch: master
- Last Pushed: 2022-12-28T20:29:46.000Z (almost 2 years ago)
- Last Synced: 2024-08-01T12:32:16.662Z (4 months ago)
- Topics: automatic-speech-recognition, python, speech-recognition, speech-to-text, transformers, wav2vec2, websockets
- Language: Python
- Homepage: https://youtu.be/gdSUyI1z50o
- Size: 118 KB
- Stars: 12
- Watchers: 2
- Forks: 2
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
[![Medium][medium-shield]][medium-url]
[![Twitter][twitter-shield]][twitter-url]
[![Linkedin][linkedin-shield]][linkedin-url]
[![YouTube][youtube-shield]][youtube-url]
# Automatic Speech Recognition
This repository contains the implementation of an Automatic Speech Recognition system in python, using a client-server architecture with Web Sockets.
If you want to know the explanation, I leave you the link to my video on YouTube.
YouTube: Speech Recognition in Your PC
## 1. Files
- The `docs` directory the list of resources used for this project.
- The `client.py` script defines the client websocket. It handles stuff related to recognizing mic, setting audio features, etc.
- The `server.py` script defines the server websocket. It handles stuff related to loading Speech Recognition Models, inference, etc.
## 2. The architecture
## 3. Dependencies
In order to install the correct versions of each dependency, it is highly suggested to work under a virtual environment. In this case, I'm using the `pipenv` environment. To install the dependencies you just need type:
```
pipenv install -r requirements.txt
```
then, in order to lauch the environment you would need to type:
```
pipenv shell
```
## 4. How to use
Once you have correctly installed the requirements. You must set in line `17` of `client.py` your input device. In my case, my device is defined as `INPUT_DEVICE = "UMC204HD 192k"`.
### Server
First, you need to launch the server. My recommendation is to use one terminail (or session) for the server. You can also run the server in background.
```
$ python -B server.py -l [EN | ES]
```
### Client
Then, you will be able to lauch the client.
```
$ python -B client.py
```
## 5. Comments
Any comment, suggestion or colaboration, just reach me out at: [email protected]
Feel free to clone or fork!
[medium-shield]: https://img.shields.io/badge/medium-%2312100E.svg?&style=for-the-badge&logo=medium&logoColor=white
[medium-url]: https://medium.com/@fer.neutron
[twitter-shield]: https://img.shields.io/badge/twitter-%231DA1F2.svg?&style=for-the-badge&logo=twitter&logoColor=white
[twitter-url]: https://twitter.com/Fernando_LpzV
[linkedin-shield]: https://img.shields.io/badge/linkedin-%230077B5.svg?&style=for-the-badge&logo=linkedin&logoColor=white
[linkedin-url]: https://www.linkedin.com/in/fernando-lopezvelasco/
[youtube-shield]: https://img.shields.io/badge/YouTube-YouTube-red
[youtube-url]: https://www.youtube.com/@ferneutron