shreejalmaharjan-27/tiktok-short-captions

Whisper model size (currently only large-v3 is supported).

Video Path

Language spoken in the audio, specify 'auto' for automatic language detection

optional patience value to use in beam decoding, as in https://arxiv.org/abs/2204.05424, the default (1.0) is equivalent to conventional beam search

temperature to use for sampling

The maximum number of words to generate in each window

optional text to provide as a prompt for the first window.

The color of the highlight for the captioned text

comma-separated list of token ids to suppress during sampling; '-1' will suppress most special characters except common punctuations

if the average log probability is lower than this value, treat the decoding as failed

if the probability of the <|nospeech|> token is higher than this value AND the decoding has failed due to `logprob_threshold`, consider the segment as silence

if True, provide the previous output of the model as a prompt for the next window; disabling may make the text inconsistent across windows, but the model becomes less prone to getting stuck in a failure loop

if the gzip compression ratio is higher than this value, treat the decoding as failed

temperature to increase when falling back when the decoding fails to meet either of the thresholds below