mirrors/whispering
1
0
Fork 0
mirror of https://github.com/shirayu/whispering.git synced 2024-11-25 10:21:00 +00:00
Code Issues Projects Releases Packages Wiki Activity
Streaming transcriber with whisper
35 commits 2 branches 9 tags 512 KiB
Python 97%
Makefile 3%
Find a file
Yuta Hayashibe 4d49b710d8 Add a setup step
2022-09-24 11:02:40 +09:00
.github Initial commit 2022-09-23 19:20:29 +09:00
whisper_streaming Add debug log 2022-09-24 10:13:10 +09:00
.gitignore Initial commit 2022-09-23 19:20:29 +09:00
.markdownlint.json Initial commit 2022-09-23 19:20:29 +09:00
LICENSE Initial commit 2022-09-23 19:20:29 +09:00
LICENSE.whisper Initial commit 2022-09-23 19:20:29 +09:00
Makefile Fix setting for isort 2022-09-23 20:05:33 +09:00
package-lock.json Initial commit 2022-09-23 19:20:29 +09:00
package.json Initial commit 2022-09-23 19:20:29 +09:00
poetry.lock Updated whisper 2022-09-24 10:55:01 +09:00
pyproject.toml Updated whisper 2022-09-24 10:55:01 +09:00
README.md Add a setup step 2022-09-24 11:02:40 +09:00
setup.cfg Fix setting for isort 2022-09-23 20:05:33 +09:00

README.md

whisper_streaming

CI CodeQL Typos

Streaming transcriber with whisper. Transcribing in real time, enough machine power is needed.

Example

# Setup
git clone https://github.com/shirayu/whisper_streaming.git
cd whisper_streaming
poetry install --only main

# If you use GPU with CUDA 11.6
poetry run pip install 'torch==1.12.0+cu116' -f https://download.pytorch.org/whl/torch_stable.html

# Run in English
poetry run whisper_streaming --language en --model base -n 20
  • --help shows full options
  • --language sets the language to transcribe. The list of languages are shown with poetry run whisper_streaming -h
  • -n sets interval of parsing. Larger values can improve accuracy but consume more memory.
  • --debug outputs logs for debug

Tips

If you get OSError: PortAudio library not found: Install portaudio

# Ubuntu
sudo apt-get install portaudio19-dev

License