isaacgv/cog-whisper – Run with an API on Replicate

isaacgv / cog-whisper

Cold

Public
465 runs
A100 (80GB)

Run with an API

Playground API Examples README Versions

Input

audio

*file

Audio file

model

string

Choose a Whisper model.

Default: "large-v2"

transcription

string

Choose the format for the transcription

Default: "plain text"

translate

boolean

Translate the text to English when set to True

Default: false

language

string

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

temperature

number

temperature to use for sampling

Default: 0

patience

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

suppress_tokens

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"

initial_prompt

string

Shift + Return to add a new line

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

condition_on_previous_text

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

temperature_increment_on_fallback

number

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

Default: 0.2

compression_ratio_threshold

number

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

Default: 2.4

logprob_threshold

number

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

Default: -1

no_speech_threshold

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

word_timestamps

boolean

Improves the accuracy of the timestamps by using word-level timestamps

Default: true

Run this model in Node.js with one line of code:

npx create-replicate --model=isaacgv/cog-whisper

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run isaacgv/cog-whisper using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "isaacgv/cog-whisper:c2e1638275200006c28d4079534577724f3918460d954784d2353d96a3aa55d3",
  {
    input: {
      model: "large-v2",
      language: "af",
      translate: false,
      temperature: 0,
      transcription: "plain text",
      suppress_tokens: "-1",
      word_timestamps: true,
      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.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run isaacgv/cog-whisper using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "isaacgv/cog-whisper:c2e1638275200006c28d4079534577724f3918460d954784d2353d96a3aa55d3",
    input={
        "model": "large-v2",
        "language": "af",
        "translate": False,
        "temperature": 0,
        "transcription": "plain text",
        "suppress_tokens": "-1",
        "word_timestamps": True,
        "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.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run isaacgv/cog-whisper using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "c2e1638275200006c28d4079534577724f3918460d954784d2353d96a3aa55d3",
    "input": {
      "model": "large-v2",
      "language": "af",
      "translate": false,
      "temperature": 0,
      "transcription": "plain text",
      "suppress_tokens": "-1",
      "word_timestamps": true,
      "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.

Output

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

Run time and cost

This model costs approximately $0.63 to run on Replicate, or 1 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 A100 (80GB) GPU hardware. Predictions typically complete within 8 minutes. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.