datong-new/vc – Run with an API on Replicate

datong-new / vc

Cold

Public
70 runs
L40S

Run with an API

Playground API Examples README Versions

Input

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

refer_video

*file

The path of the video to be referred.

text

*string

Shift + Return to add a new line

因此，没有一个固定的答案来描述所有情况下编码后字符串的具体长度，它会根据你需要编码的原始数据的大小而有所不同。对于具体情况下的精确长度，需要根据实际的原始数据和编码规则来确定。因此，没有一个固定的答案来描述所有情况下编码后字符串的具体长度，它会根据你需要编码的原始数据的大小而有所不同。对于具体情况下的精确长度，需要根据实际的原始数据和编码规则来确定。

video_language

string

The language of the video to be referred.

Default: "中文"

text_language

string

The language of the text to be referred.

Default: "中文"

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

npx create-replicate --model=datong-new/vc

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 datong-new/vc using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "datong-new/vc:c0edf71c5242cb90457701a2f44292bfc12c333aab31878ab57ee164bfc07259",
  {
    input: {
      text: "因此，没有一个固定的答案来描述所有情况下编码后字符串的具体长度，它会根据你需要编码的原始数据的大小而有所不同。对于具体情况下的精确长度，需要根据实际的原始数据和编码规则来确定。",
      refer_video: "https://replicate.delivery/pbxt/Kp95btr4Xmaj6eWm7zpQVyO5kAeEtfPvt5jL22TkYxq0H2Dr/myvoice.wav",
      text_language: "中文",
      video_language: "中文"
    }
  }
);

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 datong-new/vc using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "datong-new/vc:c0edf71c5242cb90457701a2f44292bfc12c333aab31878ab57ee164bfc07259",
    input={
        "text": "因此，没有一个固定的答案来描述所有情况下编码后字符串的具体长度，它会根据你需要编码的原始数据的大小而有所不同。对于具体情况下的精确长度，需要根据实际的原始数据和编码规则来确定。",
        "refer_video": "https://replicate.delivery/pbxt/Kp95btr4Xmaj6eWm7zpQVyO5kAeEtfPvt5jL22TkYxq0H2Dr/myvoice.wav",
        "text_language": "中文",
        "video_language": "中文"
    }
)
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 datong-new/vc 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": "datong-new/vc:c0edf71c5242cb90457701a2f44292bfc12c333aab31878ab57ee164bfc07259",
    "input": {
      "text": "因此，没有一个固定的答案来描述所有情况下编码后字符串的具体长度，它会根据你需要编码的原始数据的大小而有所不同。对于具体情况下的精确长度，需要根据实际的原始数据和编码规则来确定。",
      "refer_video": "https://replicate.delivery/pbxt/Kp95btr4Xmaj6eWm7zpQVyO5kAeEtfPvt5jL22TkYxq0H2Dr/myvoice.wav",
      "text_language": "中文",
      "video_language": "中文"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

{
  "completed_at": "2024-04-28T04:26:59.426298Z",
  "created_at": "2024-04-28T04:24:59.678000Z",
  "data_removed": false,
  "error": null,
  "id": "b1b0gaqr3srgg0cf4bs8e7nph4",
  "input": {
    "text": "因此，没有一个固定的答案来描述所有情况下编码后字符串的具体长度，它会根据你需要编码的原始数据的大小而有所不同。对于具体情况下的精确长度，需要根据实际的原始数据和编码规则来确定。",
    "refer_video": "https://replicate.delivery/pbxt/Kp95btr4Xmaj6eWm7zpQVyO5kAeEtfPvt5jL22TkYxq0H2Dr/myvoice.wav",
    "text_language": "中文",
    "video_language": "中文"
  },
  "logs": "prompt_text 对于我的电话,他回的越来越少,看向硝烟的眼神却越来越温柔,他们吵了四年的CP,从未承认,却一直暧昧。\nINFO:     127.0.0.1:37136 - \"GET /?refer_wav_path=%2Ftmp%2Ftmpun1yp9m7myvoice.wav&prompt_text=%E5%AF%B9%E4%BA%8E%E6%88%91%E7%9A%84%E7%94%B5%E8%AF%9D%2C%E4%BB%96%E5%9B%9E%E7%9A%84%E8%B6%8A%E6%9D%A5%E8%B6%8A%E5%B0%91%2C%E7%9C%8B%E5%90%91%E7%A1%9D%E7%83%9F%E7%9A%84%E7%9C%BC%E7%A5%9E%E5%8D%B4%E8%B6%8A%E6%9D%A5%E8%B6%8A%E6%B8%A9%E6%9F%94%2C%E4%BB%96%E4%BB%AC%E5%90%B5%E4%BA%86%E5%9B%9B%E5%B9%B4%E7%9A%84CP%2C%E4%BB%8E%E6%9C%AA%E6%89%BF%E8%AE%A4%2C%E5%8D%B4%E4%B8%80%E7%9B%B4%E6%9A%A7%E6%98%A7%E3%80%82&prompt_language=all_zh&text=%E5%9B%A0%E6%AD%A4%EF%BC%8C%E6%B2%A1%E6%9C%89%E4%B8%80%E4%B8%AA%E5%9B%BA%E5%AE%9A%E7%9A%84%E7%AD%94%E6%A1%88%E6%9D%A5%E6%8F%8F%E8%BF%B0%E6%89%80%E6%9C%89%E6%83%85%E5%86%B5%E4%B8%8B%E7%BC%96%E7%A0%81%E5%90%8E%E5%AD%97%E7%AC%A6%E4%B8%B2%E7%9A%84%E5%85%B7%E4%BD%93%E9%95%BF%E5%BA%A6%EF%BC%8C%E5%AE%83%E4%BC%9A%E6%A0%B9%E6%8D%AE%E4%BD%A0%E9%9C%80%E8%A6%81%E7%BC%96%E7%A0%81%E7%9A%84%E5%8E%9F%E5%A7%8B%E6%95%B0%E6%8D%AE%E7%9A%84%E5%A4%A7%E5%B0%8F%E8%80%8C%E6%9C%89%E6%89%80%E4%B8%8D%E5%90%8C%E3%80%82%E5%AF%B9%E4%BA%8E%E5%85%B7%E4%BD%93%E6%83%85%E5%86%B5%E4%B8%8B%E7%9A%84%E7%B2%BE%E7%A1%AE%E9%95%BF%E5%BA%A6%EF%BC%8C%E9%9C%80%E8%A6%81%E6%A0%B9%E6%8D%AE%E5%AE%9E%E9%99%85%E7%9A%84%E5%8E%9F%E5%A7%8B%E6%95%B0%E6%8D%AE%E5%92%8C%E7%BC%96%E7%A0%81%E8%A7%84%E5%88%99%E6%9D%A5%E7%A1%AE%E5%AE%9A%E3%80%82&text_language=all_zh HTTP/1.1\" 200 OK\nBuilding prefix dict from the default dictionary ...\nDEBUG:jieba_fast:Building prefix dict from the default dictionary ...\nDumping model to file cache /tmp/jieba.cache\nDEBUG:jieba_fast:Dumping model to file cache /tmp/jieba.cache\nLoading model cost 0.631 seconds.\nPrefix dict has been built succesfully.\nDEBUG:jieba_fast:Loading model cost 0.631 seconds.\nDEBUG:jieba_fast:Prefix dict has been built succesfully.\n  0%|          | 0/1500 [00:00<?, ?it/s]\n  0%|          | 4/1500 [00:00<00:38, 38.56it/s]\n  1%|          | 14/1500 [00:00<00:20, 72.18it/s]\n  2%|▏         | 24/1500 [00:00<00:18, 81.69it/s]\n  2%|▏         | 34/1500 [00:00<00:17, 85.85it/s]\n  3%|▎         | 44/1500 [00:00<00:16, 88.20it/s]\n  4%|▎         | 54/1500 [00:00<00:16, 89.57it/s]\n  4%|▍         | 63/1500 [00:00<00:16, 89.29it/s]\n  5%|▍         | 73/1500 [00:00<00:15, 90.09it/s]\n  6%|▌         | 83/1500 [00:00<00:15, 90.67it/s]\n  6%|▌         | 93/1500 [00:01<00:15, 91.84it/s]\n  7%|▋         | 103/1500 [00:01<00:14, 93.37it/s]\n  8%|▊         | 113/1500 [00:01<00:14, 94.55it/s]\n  8%|▊         | 123/1500 [00:01<00:14, 95.18it/s]\n  9%|▉         | 133/1500 [00:01<00:14, 95.46it/s]\n 10%|▉         | 143/1500 [00:01<00:14, 94.43it/s]\n 10%|█         | 153/1500 [00:01<00:14, 93.61it/s]\n 11%|█         | 163/1500 [00:01<00:14, 93.12it/s]\n 12%|█▏        | 173/1500 [00:01<00:14, 92.68it/s]\n 12%|█▏        | 183/1500 [00:02<00:14, 92.50it/s]\n 13%|█▎        | 193/1500 [00:02<00:14, 92.44it/s]\n 14%|█▎        | 203/1500 [00:02<00:14, 92.55it/s]\n 14%|█▍        | 213/1500 [00:02<00:13, 92.76it/s]\n 15%|█▍        | 223/1500 [00:02<00:13, 94.07it/s]\n 16%|█▌        | 233/1500 [00:02<00:13, 94.97it/s]\n 16%|█▌        | 243/1500 [00:02<00:13, 95.47it/s]\n 17%|█▋        | 253/1500 [00:02<00:13, 95.74it/s]\n 18%|█▊        | 263/1500 [00:02<00:13, 94.63it/s]\n 18%|█▊        | 273/1500 [00:02<00:13, 94.03it/s]\n 19%|█▉        | 283/1500 [00:03<00:13, 93.50it/s]\n 20%|█▉        | 293/1500 [00:03<00:12, 93.21it/s]\n 20%|██        | 303/1500 [00:03<00:12, 92.97it/s]\n 21%|██        | 313/1500 [00:03<00:12, 92.63it/s]\n 22%|██▏       | 323/1500 [00:03<00:12, 92.16it/s]\n 22%|██▏       | 333/1500 [00:03<00:12, 91.61it/s]\n 23%|██▎       | 343/1500 [00:03<00:12, 91.70it/s]\n 24%|██▎       | 353/1500 [00:03<00:12, 92.05it/s]\n 24%|██▍       | 363/1500 [00:03<00:12, 92.17it/s]\n 25%|██▍       | 373/1500 [00:04<00:12, 92.31it/s]\n 26%|██▌       | 383/1500 [00:04<00:12, 92.67it/s]\n 26%|██▌       | 393/1500 [00:04<00:11, 92.82it/s]\n 27%|██▋       | 403/1500 [00:04<00:11, 93.01it/s]\n 28%|██▊       | 413/1500 [00:04<00:11, 93.33it/s]\n 28%|██▊       | 423/1500 [00:04<00:11, 92.49it/s]\n 29%|██▉       | 433/1500 [00:04<00:11, 92.71it/s]\n 30%|██▉       | 443/1500 [00:04<00:11, 92.72it/s]\n 30%|███       | 453/1500 [00:04<00:11, 92.60it/s]\n 31%|███       | 463/1500 [00:05<00:11, 94.02it/s]\n 32%|███▏      | 473/1500 [00:05<00:10, 95.00it/s]\n 32%|███▏      | 483/1500 [00:05<00:10, 95.02it/s]\n 33%|███▎      | 493/1500 [00:05<00:10, 94.37it/s]\n 34%|███▎      | 503/1500 [00:05<00:10, 93.12it/s]\n 34%|███▍      | 513/1500 [00:05<00:10, 93.21it/s]\n 35%|███▍      | 523/1500 [00:05<00:10, 93.09it/s]\n 36%|███▌      | 533/1500 [00:05<00:10, 93.11it/s]\n 36%|███▌      | 543/1500 [00:05<00:10, 93.12it/s]\n 37%|███▋      | 553/1500 [00:05<00:10, 93.18it/s]\n 38%|███▊      | 563/1500 [00:06<00:10, 93.17it/s]\n 38%|███▊      | 573/1500 [00:06<00:09, 93.29it/s]\n 39%|███▉      | 583/1500 [00:06<00:09, 94.03it/s]\n 40%|███▉      | 593/1500 [00:06<00:09, 93.87it/s]\nT2S Decoding EOS [356 -> 963]\n 40%|████      | 603/1500 [00:06<00:09, 93.75it/s]\n40%|████      | 606/1500 [00:06<00:09, 92.30it/s]\nhuggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n/root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/torch/functional.py:650: UserWarning: stft with return_complex=False is deprecated. In a future pytorch release, stft will return complex tensors for all inputs, and return_complex=False will raise an error.\nNote: you can still call torch.view_as_real on the complex output to recover the old return format. (Triggered internally at ../aten/src/ATen/native/SpectralOps.cpp:863.)\nreturn _VF.stft(input, n_fft, hop_length, win_length, window,  # type: ignore[attr-defined]",
  "metrics": {
    "predict_time": 13.702274,
    "total_time": 119.748298
  },
  "output": {
    "audio": "https://replicate.delivery/pbxt/FF1JjIkpSSbuIZYEqapFWplwlSGppiVEsfdVmPmG5eelQwdlA/output.wav"
  },
  "started_at": "2024-04-28T04:26:45.724024Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/b1b0gaqr3srgg0cf4bs8e7nph4",
    "cancel": "https://api.replicate.com/v1/predictions/b1b0gaqr3srgg0cf4bs8e7nph4/cancel"
  },
  "version": "0e4ff17150fec894622c9df31c2d3c2ad83021fa7fb020533f4a80f7f193ff26"
}

Generated in

13.7 seconds

Tweak it ShareReport

prompt_text 对于我的电话,他回的越来越少,看向硝烟的眼神却越来越温柔,他们吵了四年的CP,从未承认,却一直暧昧。
INFO:     127.0.0.1:37136 - "GET /?refer_wav_path=%2Ftmp%2Ftmpun1yp9m7myvoice.wav&prompt_text=%E5%AF%B9%E4%BA%8E%E6%88%91%E7%9A%84%E7%94%B5%E8%AF%9D%2C%E4%BB%96%E5%9B%9E%E7%9A%84%E8%B6%8A%E6%9D%A5%E8%B6%8A%E5%B0%91%2C%E7%9C%8B%E5%90%91%E7%A1%9D%E7%83%9F%E7%9A%84%E7%9C%BC%E7%A5%9E%E5%8D%B4%E8%B6%8A%E6%9D%A5%E8%B6%8A%E6%B8%A9%E6%9F%94%2C%E4%BB%96%E4%BB%AC%E5%90%B5%E4%BA%86%E5%9B%9B%E5%B9%B4%E7%9A%84CP%2C%E4%BB%8E%E6%9C%AA%E6%89%BF%E8%AE%A4%2C%E5%8D%B4%E4%B8%80%E7%9B%B4%E6%9A%A7%E6%98%A7%E3%80%82&prompt_language=all_zh&text=%E5%9B%A0%E6%AD%A4%EF%BC%8C%E6%B2%A1%E6%9C%89%E4%B8%80%E4%B8%AA%E5%9B%BA%E5%AE%9A%E7%9A%84%E7%AD%94%E6%A1%88%E6%9D%A5%E6%8F%8F%E8%BF%B0%E6%89%80%E6%9C%89%E6%83%85%E5%86%B5%E4%B8%8B%E7%BC%96%E7%A0%81%E5%90%8E%E5%AD%97%E7%AC%A6%E4%B8%B2%E7%9A%84%E5%85%B7%E4%BD%93%E9%95%BF%E5%BA%A6%EF%BC%8C%E5%AE%83%E4%BC%9A%E6%A0%B9%E6%8D%AE%E4%BD%A0%E9%9C%80%E8%A6%81%E7%BC%96%E7%A0%81%E7%9A%84%E5%8E%9F%E5%A7%8B%E6%95%B0%E6%8D%AE%E7%9A%84%E5%A4%A7%E5%B0%8F%E8%80%8C%E6%9C%89%E6%89%80%E4%B8%8D%E5%90%8C%E3%80%82%E5%AF%B9%E4%BA%8E%E5%85%B7%E4%BD%93%E6%83%85%E5%86%B5%E4%B8%8B%E7%9A%84%E7%B2%BE%E7%A1%AE%E9%95%BF%E5%BA%A6%EF%BC%8C%E9%9C%80%E8%A6%81%E6%A0%B9%E6%8D%AE%E5%AE%9E%E9%99%85%E7%9A%84%E5%8E%9F%E5%A7%8B%E6%95%B0%E6%8D%AE%E5%92%8C%E7%BC%96%E7%A0%81%E8%A7%84%E5%88%99%E6%9D%A5%E7%A1%AE%E5%AE%9A%E3%80%82&text_language=all_zh HTTP/1.1" 200 OK
Building prefix dict from the default dictionary ...
DEBUG:jieba_fast:Building prefix dict from the default dictionary ...
Dumping model to file cache /tmp/jieba.cache
DEBUG:jieba_fast:Dumping model to file cache /tmp/jieba.cache
Loading model cost 0.631 seconds.
Prefix dict has been built succesfully.
DEBUG:jieba_fast:Loading model cost 0.631 seconds.
DEBUG:jieba_fast:Prefix dict has been built succesfully.
  0%|          | 0/1500 [00:00<?, ?it/s]
  0%|          | 4/1500 [00:00<00:38, 38.56it/s]
  1%|          | 14/1500 [00:00<00:20, 72.18it/s]
  2%|▏         | 24/1500 [00:00<00:18, 81.69it/s]
  2%|▏         | 34/1500 [00:00<00:17, 85.85it/s]
  3%|▎         | 44/1500 [00:00<00:16, 88.20it/s]
  4%|▎         | 54/1500 [00:00<00:16, 89.57it/s]
  4%|▍         | 63/1500 [00:00<00:16, 89.29it/s]
  5%|▍         | 73/1500 [00:00<00:15, 90.09it/s]
  6%|▌         | 83/1500 [00:00<00:15, 90.67it/s]
  6%|▌         | 93/1500 [00:01<00:15, 91.84it/s]
  7%|▋         | 103/1500 [00:01<00:14, 93.37it/s]
  8%|▊         | 113/1500 [00:01<00:14, 94.55it/s]
  8%|▊         | 123/1500 [00:01<00:14, 95.18it/s]
  9%|▉         | 133/1500 [00:01<00:14, 95.46it/s]
 10%|▉         | 143/1500 [00:01<00:14, 94.43it/s]
 10%|█         | 153/1500 [00:01<00:14, 93.61it/s]
 11%|█         | 163/1500 [00:01<00:14, 93.12it/s]
 12%|█▏        | 173/1500 [00:01<00:14, 92.68it/s]
 12%|█▏        | 183/1500 [00:02<00:14, 92.50it/s]
 13%|█▎        | 193/1500 [00:02<00:14, 92.44it/s]
 14%|█▎        | 203/1500 [00:02<00:14, 92.55it/s]
 14%|█▍        | 213/1500 [00:02<00:13, 92.76it/s]
 15%|█▍        | 223/1500 [00:02<00:13, 94.07it/s]
 16%|█▌        | 233/1500 [00:02<00:13, 94.97it/s]
 16%|█▌        | 243/1500 [00:02<00:13, 95.47it/s]
 17%|█▋        | 253/1500 [00:02<00:13, 95.74it/s]
 18%|█▊        | 263/1500 [00:02<00:13, 94.63it/s]
 18%|█▊        | 273/1500 [00:02<00:13, 94.03it/s]
 19%|█▉        | 283/1500 [00:03<00:13, 93.50it/s]
 20%|█▉        | 293/1500 [00:03<00:12, 93.21it/s]
 20%|██        | 303/1500 [00:03<00:12, 92.97it/s]
 21%|██        | 313/1500 [00:03<00:12, 92.63it/s]
 22%|██▏       | 323/1500 [00:03<00:12, 92.16it/s]
 22%|██▏       | 333/1500 [00:03<00:12, 91.61it/s]
 23%|██▎       | 343/1500 [00:03<00:12, 91.70it/s]
 24%|██▎       | 353/1500 [00:03<00:12, 92.05it/s]
 24%|██▍       | 363/1500 [00:03<00:12, 92.17it/s]
 25%|██▍       | 373/1500 [00:04<00:12, 92.31it/s]
 26%|██▌       | 383/1500 [00:04<00:12, 92.67it/s]
 26%|██▌       | 393/1500 [00:04<00:11, 92.82it/s]
 27%|██▋       | 403/1500 [00:04<00:11, 93.01it/s]
 28%|██▊       | 413/1500 [00:04<00:11, 93.33it/s]
 28%|██▊       | 423/1500 [00:04<00:11, 92.49it/s]
 29%|██▉       | 433/1500 [00:04<00:11, 92.71it/s]
 30%|██▉       | 443/1500 [00:04<00:11, 92.72it/s]
 30%|███       | 453/1500 [00:04<00:11, 92.60it/s]
 31%|███       | 463/1500 [00:05<00:11, 94.02it/s]
 32%|███▏      | 473/1500 [00:05<00:10, 95.00it/s]
 32%|███▏      | 483/1500 [00:05<00:10, 95.02it/s]
 33%|███▎      | 493/1500 [00:05<00:10, 94.37it/s]
 34%|███▎      | 503/1500 [00:05<00:10, 93.12it/s]
 34%|███▍      | 513/1500 [00:05<00:10, 93.21it/s]
 35%|███▍      | 523/1500 [00:05<00:10, 93.09it/s]
 36%|███▌      | 533/1500 [00:05<00:10, 93.11it/s]
 36%|███▌      | 543/1500 [00:05<00:10, 93.12it/s]
 37%|███▋      | 553/1500 [00:05<00:10, 93.18it/s]
 38%|███▊      | 563/1500 [00:06<00:10, 93.17it/s]
 38%|███▊      | 573/1500 [00:06<00:09, 93.29it/s]
 39%|███▉      | 583/1500 [00:06<00:09, 94.03it/s]
 40%|███▉      | 593/1500 [00:06<00:09, 93.87it/s]
T2S Decoding EOS [356 -> 963]
 40%|████      | 603/1500 [00:06<00:09, 93.75it/s]
40%|████      | 606/1500 [00:06<00:09, 92.30it/s]
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
To disable this warning, you can either:
- Avoid using `tokenizers` before the fork if possible
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
/root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/torch/functional.py:650: UserWarning: stft with return_complex=False is deprecated. In a future pytorch release, stft will return complex tensors for all inputs, and return_complex=False will raise an error.
Note: you can still call torch.view_as_real on the complex output to recover the old return format. (Triggered internally at ../aten/src/ATen/native/SpectralOps.cpp:863.)
return _VF.stft(input, n_fft, hop_length, win_length, window,  # type: ignore[attr-defined]

This output was created using a different version of the model, datong-new/vc:0e4ff171.

Run time and cost

This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.