https://github.com/faker2048/whisper-echo

whisper server, a server service for voice-to-text transcription using the openai whisper model, implemented in C++20.
https://github.com/faker2048/whisper-echo

Last synced: 3 months ago
JSON representation

whisper server, a server service for voice-to-text transcription using the openai whisper model, implemented in C++20.

• Host: GitHub
• URL: https://github.com/faker2048/whisper-echo
• Owner: faker2048
• License: mit
• Created: 2023-06-11T04:20:44.000Z (over 1 year ago)
• Default Branch: master
• Last Pushed: 2023-11-30T01:47:41.000Z (about 1 year ago)
• Last Synced: 2023-11-30T02:41:50.001Z (about 1 year ago)
• Language: C++
• Homepage:
• Size: 107 KB
• Stars: 4
• Watchers: 3
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Whisper websocket server

`whisper_echo` is a server service repository, tailored for voice-to-text transcription using the whisper-cpp. The service takes in audio data, processes it through the Whisper system, and returns the corresponding text transcription. Implemented in C++20, specifically designed for Nix environments.

## Getting Started

These instructions will guide you on how to clone, build, and test this project in your local Nix environment.

## Development

### Prerequisites

- [Nix package manager](https://nixos.org/download.html) installed and configured on your system.

### Installing Dependencies

This project utilizes Nix, a potent package manager that simplifies dependency management. Run the following command to install all necessary dependencies:

```bash

nix develop

```

### Building

```bash

git clone https://github.com/faker2048/whisper_echo.git

cd whisper_echo

mkdir build && cd build

cmake ..

make

```

Upon successful build, the resulting binary can be found in the `build` directory.

### Run

```bash whisper_echo

./bin/whisper_echo ./models/ggml-base.en.bin

```

Instead `./models/ggml-base.en.bin` use your own model_path

### Client

Here is a usable Python version of the client example. Run `nix develop` to enter the Python environment, and then execute `python ./whisper_echo/examples/py_client/client.py --file path/to/your_audio.wav`.

## License

This project is licensed under the MIT License.