2 releases
0.1.12 | Oct 27, 2023 |
---|---|
0.1.0 | Oct 26, 2023 |
#9 in #transcribe
34KB
876 lines
whisperd 🎙️
A simple HTTP server written in Rust for the OpenAI Whisper speech-to-text model.
Features ✨
- 🎧 Transcribe audio files
- 🔄 OpenAI API compatibility
- 🌈 Models
tiny.en
tiny
base.en
base
small.en
small
medium.en
medium
large
large-v1
- 🌎 Languages
- 🇬🇧 English (en)
- 🇨🇳 Chinese (zh)
- 🇩🇪 German (de)
- 🇪🇸 Spanish (es)
- 🇷🇺 Russian (ru)
Quickstart 🚀
- Clone this repository:
git clone https://github.com/tiero/whisperd.git
- Navigate to the repository and build:
cd whisperd
cargo build --release
- Run the server:
./target/release/whisperd serve --model_path path_to_whisper_model
Now, the server is running at http://localhost:8000
and ready to transcribe!
Usage 🛠️
CLI Commands
- Start the transcription server:
whisperd serve --port 5000 --model_path <path_to_model>
- Transcribe a given audio file (this downloads the model automatically from HuggingFace):
whisperd transcribe --audio <path_to_audio>
For more advanced options, use:
whisperd --help
Contribution 🤝
Pull requests and issues are welcome!
License 📜
This project is licensed under the MIT License - see the LICENSE file for details.
Dependencies
~30–47MB
~857K SLoC