How to get whisper to generate one word / word limited srt output

[lukesorvik]

Making this discussion since I spent a pretty long time looking for this and couldnt find anything in discussions
If you want to limit how many words are generated on an srt file you need to call the SRT Writer function with the kwarg of max_words_per_line= x

import whisper
from whisper.utils import get_writer

device = "cuda" if torch.cuda.is_available() else "cpu"
model = whisper.load_model(model_name).to(device)

language = "en" if model_name.endswith(".en") else None
subtitles = model.transcribe(self.audioPath, language=language, temperature=0.0, word_timestamps=True)

writer = get_writer("srt", output_dir=self.output_path) 
writer(subtitles, filename,  max_words_per_line=1 )