Audio file
Choose a Whisper model.
Default: "base"
Choose the format for the transcription
Default: "plain text"
Translate the text to English when set to True
Default: false
language spoken in the audio, specify None to perform language detection
temperature to use for sampling
Default: 0
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
comma-separated list of token ids to suppress during sampling; '-1' will suppress most special characters except common punctuations
Default: "-1"
optional text to provide as a prompt for the first window.
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
temperature to increase when falling back when the decoding fails to meet either of the thresholds below
Default: 0.2
if the gzip compression ratio is higher than this value, treat the decoding as failed
Default: 2.4
if the average log probability is lower than this value, treat the decoding as failed
Default: -1
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
Run this model in Node.js with one line of code:
npm install replicate
REPLICATE_API_TOKEN
export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run louismorgner/cog-whisper-cpu using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "louismorgner/cog-whisper-cpu:028831709b5a98f97555bf06d092e2bbb14fac073ffe6f2e9c7d220414a1487d", { input: { model: "base", language: "af", translate: false, temperature: 0, transcription: "plain text", suppress_tokens: "-1", logprob_threshold: -1, no_speech_threshold: 0.6, condition_on_previous_text: true, compression_ratio_threshold: 2.4, temperature_increment_on_fallback: 0.2 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
import replicate
output = replicate.run( "louismorgner/cog-whisper-cpu:028831709b5a98f97555bf06d092e2bbb14fac073ffe6f2e9c7d220414a1487d", input={ "model": "base", "language": "af", "translate": False, "temperature": 0, "transcription": "plain text", "suppress_tokens": "-1", "logprob_threshold": -1, "no_speech_threshold": 0.6, "condition_on_previous_text": True, "compression_ratio_threshold": 2.4, "temperature_increment_on_fallback": 0.2 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "louismorgner/cog-whisper-cpu:028831709b5a98f97555bf06d092e2bbb14fac073ffe6f2e9c7d220414a1487d", "input": { "model": "base", "language": "af", "translate": false, "temperature": 0, "transcription": "plain text", "suppress_tokens": "-1", "logprob_threshold": -1, "no_speech_threshold": 0.6, "condition_on_previous_text": true, "compression_ratio_threshold": 2.4, "temperature_increment_on_fallback": 0.2 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
No output yet! Press "Submit" to start a prediction.
This model runs on CPU hardware. We don't yet have enough runs of this model to provide performance information.
This model doesn't have a readme.
This model is cold. You'll get a fast response if the model is warm and already running, and a slower response if the model is cold and starting up.
Choose a file from your machine
Hint: you can also drag files onto the input