Readme
This model doesn't have a readme.
nateraw
/
audio-super-resolution
AudioSR: Versatile Audio Super-resolution at Scale
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=nateraw/audio-super-resolution
or set up a project from scratch
Install Replicate’s Node.js client library:
npm install replicateSet 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 nateraw/audio-super-resolution using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"nateraw/audio-super-resolution:0e453d5e4c2e0ef4f8d38a6167053dda09cf3c8dbca2355cde61dca55a915bc5",
{
input: {
seed: 42,
ddim_steps: 50,
input_file: "https://replicate.delivery/pbxt/JYv70XQsiZBbSmknfMhGoEb4QYbuyJ9hJkfgjyzCvh4TzPmT/music.wav",
guidance_scale: 3.5
}
}
);
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 replicateSet 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 replicateRun nateraw/audio-super-resolution using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"nateraw/audio-super-resolution:0e453d5e4c2e0ef4f8d38a6167053dda09cf3c8dbca2355cde61dca55a915bc5",
input={
"seed": 42,
"ddim_steps": 50,
"input_file": "https://replicate.delivery/pbxt/JYv70XQsiZBbSmknfMhGoEb4QYbuyJ9hJkfgjyzCvh4TzPmT/music.wav",
"guidance_scale": 3.5
}
)
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 nateraw/audio-super-resolution 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": "0e453d5e4c2e0ef4f8d38a6167053dda09cf3c8dbca2355cde61dca55a915bc5",
"input": {
"seed": 42,
"ddim_steps": 50,
"input_file": "https://replicate.delivery/pbxt/JYv70XQsiZBbSmknfMhGoEb4QYbuyJ9hJkfgjyzCvh4TzPmT/music.wav",
"guidance_scale": 3.5
}
}' \
https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Add a payment method to run this model.
Sign in with GitHub
By signing in, you agree to our
terms of service and privacy policy
Output
Video Player is loading.
Current Time 00:00:000
/
Duration 00:00:000
Loaded: 0%
00:00:000
Stream Type LIVE
Remaining Time -00:00:000
1x
- Chapters
- descriptions off, selected
- captions settings, opens captions settings dialog
- captions off, selected
This is a modal window.
Beginning of dialog window. Escape will cancel and close the window.
End of dialog window.
{
"completed_at": "2023-09-20T19:19:06.183902Z",
"created_at": "2023-09-20T19:17:04.700648Z",
"data_removed": false,
"error": null,
"id": "qqynzilbxm2t5h6eaywx2p7g54",
"input": {
"seed": 42,
"ddim_steps": 50,
"input_file": "https://replicate.delivery/pbxt/JYv70XQsiZBbSmknfMhGoEb4QYbuyJ9hJkfgjyzCvh4TzPmT/music.wav",
"guidance_scale": 3.5
},
"logs": "\u001b[93m Warning: audio is longer than 10.24 seconds, may degrade the model performance. It's recommand to truncate your audio to 5.12 seconds before input to AudioSR to get the best performance.\u001b[00m\n/src/audiosr/utils.py:109: FutureWarning: Pass sr=48000, n_fft=2048, n_mels=256, fmin=20, fmax=24000 as keyword args. From version 0.10 passing these as positional arguments will result in an error\nmel = librosa_mel_fn(sampling_rate, filter_length, n_mel, mel_fmin, mel_fmax)\nRunning DDIM Sampling with 50 timesteps\nDDIM Sampler: 0%| | 0/50 [00:00<?, ?it/s]\nDDIM Sampler: 2%|▏ | 1/50 [00:06<05:20, 6.54s/it]\nDDIM Sampler: 4%|▍ | 2/50 [00:06<02:14, 2.80s/it]\nDDIM Sampler: 6%|▌ | 3/50 [00:06<01:15, 1.60s/it]\nDDIM Sampler: 8%|▊ | 4/50 [00:07<00:47, 1.04s/it]\nDDIM Sampler: 10%|█ | 5/50 [00:07<00:32, 1.37it/s]\nDDIM Sampler: 12%|█▏ | 6/50 [00:07<00:23, 1.84it/s]\nDDIM Sampler: 14%|█▍ | 7/50 [00:07<00:18, 2.36it/s]\nDDIM Sampler: 16%|█▌ | 8/50 [00:07<00:14, 2.89it/s]\nDDIM Sampler: 18%|█▊ | 9/50 [00:07<00:12, 3.40it/s]\nDDIM Sampler: 20%|██ | 10/50 [00:08<00:10, 3.86it/s]\nDDIM Sampler: 22%|██▏ | 11/50 [00:08<00:09, 4.26it/s]\nDDIM Sampler: 24%|██▍ | 12/50 [00:08<00:08, 4.59it/s]\nDDIM Sampler: 26%|██▌ | 13/50 [00:08<00:07, 4.85it/s]\nDDIM Sampler: 28%|██▊ | 14/50 [00:08<00:07, 5.04it/s]\nDDIM Sampler: 30%|███ | 15/50 [00:09<00:06, 5.19it/s]\nDDIM Sampler: 32%|███▏ | 16/50 [00:09<00:06, 5.29it/s]\nDDIM Sampler: 34%|███▍ | 17/50 [00:09<00:06, 5.37it/s]\nDDIM Sampler: 36%|███▌ | 18/50 [00:09<00:05, 5.42it/s]\nDDIM Sampler: 38%|███▊ | 19/50 [00:09<00:05, 5.46it/s]\nDDIM Sampler: 40%|████ | 20/50 [00:09<00:05, 5.49it/s]\nDDIM Sampler: 42%|████▏ | 21/50 [00:10<00:05, 5.51it/s]\nDDIM Sampler: 44%|████▍ | 22/50 [00:10<00:05, 5.53it/s]\nDDIM Sampler: 46%|████▌ | 23/50 [00:10<00:04, 5.54it/s]\nDDIM Sampler: 48%|████▊ | 24/50 [00:10<00:04, 5.55it/s]\nDDIM Sampler: 50%|█████ | 25/50 [00:10<00:04, 5.55it/s]\nDDIM Sampler: 52%|█████▏ | 26/50 [00:11<00:04, 5.56it/s]\nDDIM Sampler: 54%|█████▍ | 27/50 [00:11<00:04, 5.56it/s]\nDDIM Sampler: 56%|█████▌ | 28/50 [00:11<00:03, 5.56it/s]\nDDIM Sampler: 58%|█████▊ | 29/50 [00:11<00:03, 5.56it/s]\nDDIM Sampler: 60%|██████ | 30/50 [00:11<00:03, 5.56it/s]\nDDIM Sampler: 62%|██████▏ | 31/50 [00:11<00:03, 5.56it/s]\nDDIM Sampler: 64%|██████▍ | 32/50 [00:12<00:03, 5.48it/s]\nDDIM Sampler: 66%|██████▌ | 33/50 [00:12<00:03, 5.50it/s]\nDDIM Sampler: 68%|██████▊ | 34/50 [00:12<00:02, 5.44it/s]\nDDIM Sampler: 70%|███████ | 35/50 [00:12<00:02, 5.23it/s]\nDDIM Sampler: 72%|███████▏ | 36/50 [00:12<00:02, 5.08it/s]\nDDIM Sampler: 74%|███████▍ | 37/50 [00:13<00:02, 4.99it/s]\nDDIM Sampler: 76%|███████▌ | 38/50 [00:13<00:02, 4.85it/s]\nDDIM Sampler: 78%|███████▊ | 39/50 [00:13<00:02, 4.74it/s]\nDDIM Sampler: 80%|████████ | 40/50 [00:13<00:02, 4.71it/s]\nDDIM Sampler: 82%|████████▏ | 41/50 [00:13<00:01, 4.69it/s]\nDDIM Sampler: 84%|████████▍ | 42/50 [00:14<00:01, 4.68it/s]\nDDIM Sampler: 86%|████████▌ | 43/50 [00:14<00:01, 4.68it/s]\nDDIM Sampler: 88%|████████▊ | 44/50 [00:14<00:01, 4.81it/s]\nDDIM Sampler: 90%|█████████ | 45/50 [00:14<00:00, 5.01it/s]\nDDIM Sampler: 92%|█████████▏| 46/50 [00:14<00:00, 5.16it/s]\nDDIM Sampler: 94%|█████████▍| 47/50 [00:15<00:00, 5.28it/s]\nDDIM Sampler: 96%|█████████▌| 48/50 [00:15<00:00, 5.36it/s]\nDDIM Sampler: 98%|█████████▊| 49/50 [00:15<00:00, 5.42it/s]\nDDIM Sampler: 100%|██████████| 50/50 [00:15<00:00, 5.46it/s]\nDDIM Sampler: 100%|██████████| 50/50 [00:15<00:00, 3.19it/s]",
"metrics": {
"predict_time": 32.909901,
"total_time": 121.483254
},
"output": "https://pbxt.replicate.delivery/73xEQwFed8UXSCQpBJuLYgg8ym0vjp2nSidaqWKwcxhUvHzIA/out.wav",
"started_at": "2023-09-20T19:18:33.274001Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/qqynzilbxm2t5h6eaywx2p7g54",
"cancel": "https://api.replicate.com/v1/predictions/qqynzilbxm2t5h6eaywx2p7g54/cancel"
},
"version": "9c3d3e39fb0cb6aea677264881d8073f835336137b39fdea4e94093319379535"
}Generated in
Warning: audio is longer than 10.24 seconds, may degrade the model performance. It's recommand to truncate your audio to 5.12 seconds before input to AudioSR to get the best performance.
/src/audiosr/utils.py:109: FutureWarning: Pass sr=48000, n_fft=2048, n_mels=256, fmin=20, fmax=24000 as keyword args. From version 0.10 passing these as positional arguments will result in an error
mel = librosa_mel_fn(sampling_rate, filter_length, n_mel, mel_fmin, mel_fmax)
Running DDIM Sampling with 50 timesteps
DDIM Sampler: 0%| | 0/50 [00:00<?, ?it/s]
DDIM Sampler: 2%|▏ | 1/50 [00:06<05:20, 6.54s/it]
DDIM Sampler: 4%|▍ | 2/50 [00:06<02:14, 2.80s/it]
DDIM Sampler: 6%|▌ | 3/50 [00:06<01:15, 1.60s/it]
DDIM Sampler: 8%|▊ | 4/50 [00:07<00:47, 1.04s/it]
DDIM Sampler: 10%|█ | 5/50 [00:07<00:32, 1.37it/s]
DDIM Sampler: 12%|█▏ | 6/50 [00:07<00:23, 1.84it/s]
DDIM Sampler: 14%|█▍ | 7/50 [00:07<00:18, 2.36it/s]
DDIM Sampler: 16%|█▌ | 8/50 [00:07<00:14, 2.89it/s]
DDIM Sampler: 18%|█▊ | 9/50 [00:07<00:12, 3.40it/s]
DDIM Sampler: 20%|██ | 10/50 [00:08<00:10, 3.86it/s]
DDIM Sampler: 22%|██▏ | 11/50 [00:08<00:09, 4.26it/s]
DDIM Sampler: 24%|██▍ | 12/50 [00:08<00:08, 4.59it/s]
DDIM Sampler: 26%|██▌ | 13/50 [00:08<00:07, 4.85it/s]
DDIM Sampler: 28%|██▊ | 14/50 [00:08<00:07, 5.04it/s]
DDIM Sampler: 30%|███ | 15/50 [00:09<00:06, 5.19it/s]
DDIM Sampler: 32%|███▏ | 16/50 [00:09<00:06, 5.29it/s]
DDIM Sampler: 34%|███▍ | 17/50 [00:09<00:06, 5.37it/s]
DDIM Sampler: 36%|███▌ | 18/50 [00:09<00:05, 5.42it/s]
DDIM Sampler: 38%|███▊ | 19/50 [00:09<00:05, 5.46it/s]
DDIM Sampler: 40%|████ | 20/50 [00:09<00:05, 5.49it/s]
DDIM Sampler: 42%|████▏ | 21/50 [00:10<00:05, 5.51it/s]
DDIM Sampler: 44%|████▍ | 22/50 [00:10<00:05, 5.53it/s]
DDIM Sampler: 46%|████▌ | 23/50 [00:10<00:04, 5.54it/s]
DDIM Sampler: 48%|████▊ | 24/50 [00:10<00:04, 5.55it/s]
DDIM Sampler: 50%|█████ | 25/50 [00:10<00:04, 5.55it/s]
DDIM Sampler: 52%|█████▏ | 26/50 [00:11<00:04, 5.56it/s]
DDIM Sampler: 54%|█████▍ | 27/50 [00:11<00:04, 5.56it/s]
DDIM Sampler: 56%|█████▌ | 28/50 [00:11<00:03, 5.56it/s]
DDIM Sampler: 58%|█████▊ | 29/50 [00:11<00:03, 5.56it/s]
DDIM Sampler: 60%|██████ | 30/50 [00:11<00:03, 5.56it/s]
DDIM Sampler: 62%|██████▏ | 31/50 [00:11<00:03, 5.56it/s]
DDIM Sampler: 64%|██████▍ | 32/50 [00:12<00:03, 5.48it/s]
DDIM Sampler: 66%|██████▌ | 33/50 [00:12<00:03, 5.50it/s]
DDIM Sampler: 68%|██████▊ | 34/50 [00:12<00:02, 5.44it/s]
DDIM Sampler: 70%|███████ | 35/50 [00:12<00:02, 5.23it/s]
DDIM Sampler: 72%|███████▏ | 36/50 [00:12<00:02, 5.08it/s]
DDIM Sampler: 74%|███████▍ | 37/50 [00:13<00:02, 4.99it/s]
DDIM Sampler: 76%|███████▌ | 38/50 [00:13<00:02, 4.85it/s]
DDIM Sampler: 78%|███████▊ | 39/50 [00:13<00:02, 4.74it/s]
DDIM Sampler: 80%|████████ | 40/50 [00:13<00:02, 4.71it/s]
DDIM Sampler: 82%|████████▏ | 41/50 [00:13<00:01, 4.69it/s]
DDIM Sampler: 84%|████████▍ | 42/50 [00:14<00:01, 4.68it/s]
DDIM Sampler: 86%|████████▌ | 43/50 [00:14<00:01, 4.68it/s]
DDIM Sampler: 88%|████████▊ | 44/50 [00:14<00:01, 4.81it/s]
DDIM Sampler: 90%|█████████ | 45/50 [00:14<00:00, 5.01it/s]
DDIM Sampler: 92%|█████████▏| 46/50 [00:14<00:00, 5.16it/s]
DDIM Sampler: 94%|█████████▍| 47/50 [00:15<00:00, 5.28it/s]
DDIM Sampler: 96%|█████████▌| 48/50 [00:15<00:00, 5.36it/s]
DDIM Sampler: 98%|█████████▊| 49/50 [00:15<00:00, 5.42it/s]
DDIM Sampler: 100%|██████████| 50/50 [00:15<00:00, 5.46it/s]
DDIM Sampler: 100%|██████████| 50/50 [00:15<00:00, 3.19it/s]This example was created by a different version, nateraw/audio-super-resolution:9c3d3e39.
Run time and cost
This model costs approximately $0.030 to run on Replicate, or 33 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 L40S GPU hardware. Predictions typically complete within 31 seconds. The predict time for this model varies significantly based on the inputs.