chrissewell/whisperX
1
0
Fork 0
mirror of https://github.com/m-bain/whisperX.git synced 2025-07-01 18:17:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #430 from dotgrid/dotgrid-docs-patch

Browse Source 
Document --compute_type command line option
This commit is contained in:
Max Bain
2023-08-29 10:02:51 -06:00
committed by GitHub
parent ef965a03ed c1197c490e
commit 3c7b03935b
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -127,6 +127,10 @@ To label the transcript with speaker ID's (set number of speakers if known e.g.
whisperx examples/sample01.wav --model large-v2 --diarize --highlight_words True whisperx examples/sample01.wav --model large-v2 --diarize --highlight_words True
To run on CPU instead of GPU (and for running on Mac OS X):
whisperx examples/sample01.wav --compute_type int8
### Other languages ### Other languages
The phoneme ASR alignment model is *language-specific*, for tested languages these models are [automatically picked from torchaudio pipelines or huggingface](https://github.com/m-bain/whisperX/blob/e909f2f766b23b2000f2d95df41f9b844ac53e49/whisperx/transcribe.py#L22). The phoneme ASR alignment model is *language-specific*, for tested languages these models are [automatically picked from torchaudio pipelines or huggingface](https://github.com/m-bain/whisperX/blob/e909f2f766b23b2000f2d95df41f9b844ac53e49/whisperx/transcribe.py#L22).