https://github.com/andreykolomiets/local_speech_translator

Almost online speech translation on Apple Silicon laptops with CoreML enabled. Doesn't need any APIs, all work is done locally using OpenAI's excellent Whisper model. Also https://github.com/ggerganov/whisper.cpp repo is used to build Whisper with CoreML support, enhancing speed significantly
https://github.com/andreykolomiets/local_speech_translator

coreml dash fastapi hebrew hebrew-english whisper whisper-cpp

Last synced: about 3 hours ago
JSON representation

Almost online speech translation on Apple Silicon laptops with CoreML enabled. Doesn't need any APIs, all work is done locally using OpenAI's excellent Whisper model. Also https://github.com/ggerganov/whisper.cpp repo is used to build Whisper with CoreML support, enhancing speed significantly

• Host: GitHub
• URL: https://github.com/andreykolomiets/local_speech_translator
• Owner: AndreyKolomiets
• Created: 2024-12-06T16:13:42.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2025-02-04T08:08:18.000Z (3 days ago)
• Last Synced: 2025-02-04T09:20:32.602Z (3 days ago)
• Topics: coreml, dash, fastapi, hebrew, hebrew-english, whisper, whisper-cpp
• Language: Python
• Homepage:
• Size: 7.81 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
usage: `./run_all.sh  ` 

need to fill `.env` file first with the following variables:

```

DEFAULT_INPUT_DEVICE_NAME = 

EXECUTABLE_PATH = 

MODEL_PATH = 

```

jupyter notebook will list all the devices available

ui will start at http://127.0.0.1:8050/

Tested on python 3.10