daanelson / whisper-sandbox

Test model for whisper improvements

  • Public
  • 166 runs
  • T4
  • GitHub

Input

*file

Audio file

string

Choose a Whisper model.

Default: "large-v2"

string

Choose the format for the transcription

Default: "plain text"

boolean

Translate the text to English when set to True

Default: false

string

language spoken in the audio, specify None to perform language detection

number

temperature to use for sampling

Default: 0

number

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

string
Shift + Return to add a new line

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

Default: "-1"

string
Shift + Return to add a new line

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

boolean

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

Default: true

number

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

Default: 0.2

number

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

Default: 2.4

number

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

Default: -1

number

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

Default: 0.6

Output

No output yet! Press "Submit" to start a prediction.

Run time and cost

This model costs approximately $0.0022 to run on Replicate, or 454 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 10 seconds.

Readme

Model description

Intended use

Ethical considerations

Caveats and recommendations