zsxkib/whisper-lazyloading:2ebca49b – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

zsxkib /whisper-lazyloading:2ebca49b

Playground API

Input

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

audio

*file

Audio file

model

string

Whisper model size. Changing models incurs overhead for loading. For large-v3 only, consider using https://replicate.com/openai/whisper

Default: "large-v3"

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 'auto' for automatic language detection

Default: "auto"

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

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

npx create-replicate --model=zsxkib/whisper-lazyloading

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

const output = await replicate.run(
  "zsxkib/whisper-lazyloading:2ebca49b6d1c835019ddd5a0a3429b76094c8f37fdefa92a5ef6f05a68bf3746",
  {
    input: {
      audio: "https://replicate.delivery/mgxm/e5159b1b-508a-4be4-b892-e1eb47850bdc/OSR_uk_000_0050_8k.wav",
      model: "base",
      language: "auto",
      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.

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

output = replicate.run(
    "zsxkib/whisper-lazyloading:2ebca49b6d1c835019ddd5a0a3429b76094c8f37fdefa92a5ef6f05a68bf3746",
    input={
        "audio": "https://replicate.delivery/mgxm/e5159b1b-508a-4be4-b892-e1eb47850bdc/OSR_uk_000_0050_8k.wav",
        "model": "base",
        "language": "auto",
        "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.

Set the REPLICATE_API_TOKEN environment variable:

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

Find your API token in your account settings.

Run zsxkib/whisper-lazyloading 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": "2ebca49b6d1c835019ddd5a0a3429b76094c8f37fdefa92a5ef6f05a68bf3746",
    "input": {
      "audio": "https://replicate.delivery/mgxm/e5159b1b-508a-4be4-b892-e1eb47850bdc/OSR_uk_000_0050_8k.wav",
      "model": "base",
      "language": "auto",
      "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.

Output

segments

[ { "id": 0, "end": 11.24, "seek": 0, "text": " The little tails they tell are false. The door was barred, locked and bolted as well.", "start": 0, "tokens": [ 50364, 440, 707, 28537, 436, 980, 366, 7908, 13, 440, 2853, 390, 2159, 986, 11, 9376, 293, 13436, 292, 382, 731, 13, 50926 ], "avg_logprob": -0.14770180246104364, "temperature": 0, "no_speech_prob": 0.08406414091587067, "compression_ratio": 1.4795321637426901 }, { "id": 1, "end": 19.56, "seek": 0, "text": " Right pairs are fit for a queen's table. A big wet stain was on the round carpet.", "start": 11.24, "tokens": [ 50926, 1779, 15494, 366, 3318, 337, 257, 12206, 311, 3199, 13, 316, 955, 6630, 16441, 390, 322, 264, 3098, 18119, 13, 51342 ], "avg_logprob": -0.14770180246104364, "temperature": 0, "no_speech_prob": 0.08406414091587067, "compression_ratio": 1.4795321637426901 }, { "id": 2, "end": 28.88, "seek": 0, "text": " The kite dipped and swayed but stayed aloft. The pleasant hours fly by much too soon.", "start": 19.56, "tokens": [ 51342, 440, 38867, 45162, 293, 27555, 292, 457, 9181, 419, 6750, 13, 440, 16232, 2496, 3603, 538, 709, 886, 2321, 13, 51808 ], "avg_logprob": -0.14770180246104364, "temperature": 0, "no_speech_prob": 0.08406414091587067, "compression_ratio": 1.4795321637426901 }, { "id": 3, "end": 37.28, "seek": 2888, "text": " The room was crowded with a mild wob. The room was crowded with a wild mob.", "start": 28.88, "tokens": [ 50364, 440, 1808, 390, 21634, 365, 257, 15154, 261, 996, 13, 440, 1808, 390, 21634, 365, 257, 4868, 4298, 13, 50784 ], "avg_logprob": -0.23257136344909668, "temperature": 0, "no_speech_prob": 0.0029556467197835445, "compression_ratio": 1.5461538461538462 }, { "id": 4, "end": 46.36, "seek": 2888, "text": " This strong arm shall shield your honour. She blushed when he gave her a white orchid.", "start": 37.28, "tokens": [ 50784, 639, 2068, 3726, 4393, 10257, 428, 20631, 13, 1240, 25218, 292, 562, 415, 2729, 720, 257, 2418, 34850, 327, 13, 51238 ], "avg_logprob": -0.23257136344909668, "temperature": 0, "no_speech_prob": 0.0029556467197835445, "compression_ratio": 1.5461538461538462 }, { "id": 5, "end": 48.519999999999996, "seek": 2888, "text": " The beetle droned in the hot June sun.", "start": 46.36, "tokens": [ 51238, 440, 49735, 1224, 19009, 294, 264, 2368, 6928, 3295, 13, 51346 ], "avg_logprob": -0.23257136344909668, "temperature": 0, "no_speech_prob": 0.0029556467197835445, "compression_ratio": 1.5461538461538462 } ]

transcription

The little tails they tell are false. The door was barred, locked and bolted as well. Right pairs are fit for a queen's table. A big wet stain was on the round carpet. The kite dipped and swayed but stayed aloft. The pleasant hours fly by much too soon. The room was crowded with a mild wob. The room was crowded with a wild mob. This strong arm shall shield your honour. She blushed when he gave her a white orchid. The beetle droned in the hot June sun.

detected_language

english

{
  "completed_at": "2024-07-01T19:30:47.441985Z",
  "created_at": "2024-07-01T19:27:18.278000Z",
  "data_removed": false,
  "error": null,
  "id": "ke6nbm0f0srgc0cgdz296vapxr",
  "input": {
    "audio": "https://replicate.delivery/mgxm/e5159b1b-508a-4be4-b892-e1eb47850bdc/OSR_uk_000_0050_8k.wav",
    "model": "base",
    "language": "auto",
    "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
  },
  "logs": "Transcribe with base model.\n[!] Initiating download from URL:  https://weights.replicate.delivery/default/whisper-v3/weights/base.pt\n[~] Destination path:  weights/base.pt\n[~] Running command: pget -vf https://weights.replicate.delivery/default/whisper-v3/weights/base.pt weights/base.pt\n2024-07-01T19:30:41Z | DEBUG | [ Waiting on Lock ] blocking_lock_acquire=false\n2024-07-01T19:30:41Z | INFO  | [ Initiating ] chunk_size=150M dest=weights/base.pt url=https://weights.replicate.delivery/default/whisper-v3/weights/base.pt\n2024-07-01T19:30:41Z | INFO  | [ Redirect ] redirect_url=https://public-weights.replicate.delivery/whisper-v3/weights/base.pt url=https://weights.replicate.delivery/default/whisper-v3/weights/base.pt\n2024-07-01T19:30:44Z | INFO  | [ Complete ] dest=weights/base.pt size=\"145 MB\" total_elapsed=3.285s url=https://weights.replicate.delivery/default/whisper-v3/weights/base.pt\n[+] Download completed in:  3.3241584300994873 seconds\nDetected language: English\n  0%|          | 0/5241 [00:00<?, ?frames/s]\n 55%|█████▌    | 2888/5241 [00:00<00:00, 3178.20frames/s]\n100%|██████████| 5241/5241 [00:01<00:00, 3528.00frames/s]\n100%|██████████| 5241/5241 [00:01<00:00, 3464.40frames/s]",
  "metrics": {
    "predict_time": 6.336608086,
    "total_time": 209.163985
  },
  "output": {
    "segments": [
      {
        "id": 0,
        "end": 11.24,
        "seek": 0,
        "text": " The little tails they tell are false. The door was barred, locked and bolted as well.",
        "start": 0,
        "tokens": [
          50364,
          440,
          707,
          28537,
          436,
          980,
          366,
          7908,
          13,
          440,
          2853,
          390,
          2159,
          986,
          11,
          9376,
          293,
          13436,
          292,
          382,
          731,
          13,
          50926
        ],
        "avg_logprob": -0.14770180246104364,
        "temperature": 0,
        "no_speech_prob": 0.08406414091587067,
        "compression_ratio": 1.4795321637426901
      },
      {
        "id": 1,
        "end": 19.56,
        "seek": 0,
        "text": " Right pairs are fit for a queen's table. A big wet stain was on the round carpet.",
        "start": 11.24,
        "tokens": [
          50926,
          1779,
          15494,
          366,
          3318,
          337,
          257,
          12206,
          311,
          3199,
          13,
          316,
          955,
          6630,
          16441,
          390,
          322,
          264,
          3098,
          18119,
          13,
          51342
        ],
        "avg_logprob": -0.14770180246104364,
        "temperature": 0,
        "no_speech_prob": 0.08406414091587067,
        "compression_ratio": 1.4795321637426901
      },
      {
        "id": 2,
        "end": 28.88,
        "seek": 0,
        "text": " The kite dipped and swayed but stayed aloft. The pleasant hours fly by much too soon.",
        "start": 19.56,
        "tokens": [
          51342,
          440,
          38867,
          45162,
          293,
          27555,
          292,
          457,
          9181,
          419,
          6750,
          13,
          440,
          16232,
          2496,
          3603,
          538,
          709,
          886,
          2321,
          13,
          51808
        ],
        "avg_logprob": -0.14770180246104364,
        "temperature": 0,
        "no_speech_prob": 0.08406414091587067,
        "compression_ratio": 1.4795321637426901
      },
      {
        "id": 3,
        "end": 37.28,
        "seek": 2888,
        "text": " The room was crowded with a mild wob. The room was crowded with a wild mob.",
        "start": 28.88,
        "tokens": [
          50364,
          440,
          1808,
          390,
          21634,
          365,
          257,
          15154,
          261,
          996,
          13,
          440,
          1808,
          390,
          21634,
          365,
          257,
          4868,
          4298,
          13,
          50784
        ],
        "avg_logprob": -0.23257136344909668,
        "temperature": 0,
        "no_speech_prob": 0.0029556467197835445,
        "compression_ratio": 1.5461538461538462
      },
      {
        "id": 4,
        "end": 46.36,
        "seek": 2888,
        "text": " This strong arm shall shield your honour. She blushed when he gave her a white orchid.",
        "start": 37.28,
        "tokens": [
          50784,
          639,
          2068,
          3726,
          4393,
          10257,
          428,
          20631,
          13,
          1240,
          25218,
          292,
          562,
          415,
          2729,
          720,
          257,
          2418,
          34850,
          327,
          13,
          51238
        ],
        "avg_logprob": -0.23257136344909668,
        "temperature": 0,
        "no_speech_prob": 0.0029556467197835445,
        "compression_ratio": 1.5461538461538462
      },
      {
        "id": 5,
        "end": 48.519999999999996,
        "seek": 2888,
        "text": " The beetle droned in the hot June sun.",
        "start": 46.36,
        "tokens": [
          51238,
          440,
          49735,
          1224,
          19009,
          294,
          264,
          2368,
          6928,
          3295,
          13,
          51346
        ],
        "avg_logprob": -0.23257136344909668,
        "temperature": 0,
        "no_speech_prob": 0.0029556467197835445,
        "compression_ratio": 1.5461538461538462
      }
    ],
    "translation": null,
    "transcription": " The little tails they tell are false. The door was barred, locked and bolted as well. Right pairs are fit for a queen's table. A big wet stain was on the round carpet. The kite dipped and swayed but stayed aloft. The pleasant hours fly by much too soon. The room was crowded with a mild wob. The room was crowded with a wild mob. This strong arm shall shield your honour. She blushed when he gave her a white orchid. The beetle droned in the hot June sun.",
    "detected_language": "english"
  },
  "started_at": "2024-07-01T19:30:41.105377Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ke6nbm0f0srgc0cgdz296vapxr",
    "cancel": "https://api.replicate.com/v1/predictions/ke6nbm0f0srgc0cgdz296vapxr/cancel"
  },
  "version": "2ebca49b6d1c835019ddd5a0a3429b76094c8f37fdefa92a5ef6f05a68bf3746"
}

Generated in

6.3 seconds

Tweak it Share Report