AtHeartEngineering/local_transcription

mirror of https://github.com/AtHeartEngineering/local_transcription.git synced 2026-01-06 22:24:09 -05:00

Go to file

AtHeartEngineer a44ef06a41 rt

2024-03-14 22:29:13 -04:00

.gitignore

updated gitignore

2024-03-11 08:09:29 -04:00

client_upload.py

init

2024-03-11 07:53:21 -04:00

format.py

added srt format

2024-03-11 08:07:18 -04:00

host.py

added srt format

2024-03-11 08:07:18 -04:00

LICENSE

Initial commit

2024-03-11 07:48:07 -04:00

local_realtime.py

rt

2024-03-14 22:29:13 -04:00

README.md

init

2024-03-11 07:53:21 -04:00

requirements.txt

init

2024-03-11 07:53:21 -04:00

settings.toml.example

init

2024-03-11 07:53:21 -04:00

utils.py

rt

2024-03-14 22:29:13 -04:00

whisper_transcriber.py

rt

2024-03-14 22:29:13 -04:00

whisperx_test.py

init

2024-03-11 07:53:21 -04:00

README.md

local_transcription

Settings

Make sure to set the IP, port, and HuggingFace API key in the settings.toml file. The huggingface API key is used to fetch the models, everything else is ran locally.

[host]
ip="192.168.0.99"
port=5063

[settings]
upload_folder="uploads"
model_folder="models"
hf_token="HUGGINGFACE API KEY"

Usage

python host.py on the server

python client_upload.py audio.mp3 on the client