Readme
fine tuned stable audio
ardianfe / stable-audio-2
music generation with fine tuned stable audio
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=ardianfe/stable-audio-2
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 ardianfe/stable-audio-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"ardianfe/stable-audio-2:6761efad154cb36efc2b10bb5432b561e3ce2557130557b34f9fd4874a894c84",
{
input: {
seed: -1,
steps: 100,
prompt: "acoustic guitar",
song_id: 10001,
cfg_scale: 6,
sigma_max: 500,
sigma_min: 0.03,
batch_size: 1,
sampler_type: "dpmpp-3m-sde",
output_format: "mp3",
seconds_start: 0,
seconds_total: 60,
negative_prompt: "",
init_noise_level: 1
}
}
);
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 ardianfe/stable-audio-2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"ardianfe/stable-audio-2:6761efad154cb36efc2b10bb5432b561e3ce2557130557b34f9fd4874a894c84",
input={
"seed": -1,
"steps": 100,
"prompt": "acoustic guitar",
"song_id": 10001,
"cfg_scale": 6,
"sigma_max": 500,
"sigma_min": 0.03,
"batch_size": 1,
"sampler_type": "dpmpp-3m-sde",
"output_format": "mp3",
"seconds_start": 0,
"seconds_total": 60,
"negative_prompt": "",
"init_noise_level": 1
}
)
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 ardianfe/stable-audio-2 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": "ardianfe/stable-audio-2:6761efad154cb36efc2b10bb5432b561e3ce2557130557b34f9fd4874a894c84",
"input": {
"seed": -1,
"steps": 100,
"prompt": "acoustic guitar",
"song_id": 10001,
"cfg_scale": 6,
"sigma_max": 500,
"sigma_min": 0.03,
"batch_size": 1,
"sampler_type": "dpmpp-3m-sde",
"output_format": "mp3",
"seconds_start": 0,
"seconds_total": 60,
"negative_prompt": "",
"init_noise_level": 1
}
}' \
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
{
"output": "https://storage.googleapis.com/lagoe_prod_generated_songs/10001/10001.mp3"
}
{
"completed_at": "2024-10-16T00:07:47.521407Z",
"created_at": "2024-10-16T00:06:43.544000Z",
"data_removed": false,
"error": null,
"id": "5z7whv7rb1rgg0cjjajtny239m",
"input": {
"seed": -1,
"steps": 100,
"prompt": "acoustic guitar",
"song_id": 10001,
"cfg_scale": 6,
"sigma_max": 500,
"sigma_min": 0.03,
"batch_size": 1,
"sampler_type": "dpmpp-3m-sde",
"output_format": "mp3",
"seconds_start": 0,
"seconds_total": 60,
"negative_prompt": "",
"init_noise_level": 1
},
"logs": "Prompt: acoustic guitar\n2228991867\n/src/stable_audio_tools/models/conditioners.py:314: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead.\nwith torch.cuda.amp.autocast(dtype=torch.float16) and torch.set_grad_enabled(self.enable_grad):\n/src/stable_audio_tools/inference/sampling.py:177: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead.\nwith torch.cuda.amp.autocast():\n 0%| | 0/100 [00:00<?, ?it/s]/root/.pyenv/versions/3.10.14/lib/python3.10/contextlib.py:103: FutureWarning: `torch.backends.cuda.sdp_kernel()` is deprecated. In the future, this context manager will be removed. Please see `torch.nn.attention.sdpa_kernel()` for the new context manager, with updated signature.\nself.gen = func(*args, **kwds)\n 1%| | 1/100 [00:00<00:18, 5.39it/s]\n 2%|▏ | 2/100 [00:00<00:13, 7.33it/s]\n 3%|▎ | 3/100 [00:00<00:11, 8.28it/s]\n 4%|▍ | 4/100 [00:00<00:10, 8.84it/s]\n 5%|▌ | 5/100 [00:00<00:10, 9.17it/s]\n 6%|▌ | 6/100 [00:00<00:10, 9.39it/s]\n 7%|▋ | 7/100 [00:00<00:09, 9.54it/s]\n 8%|▊ | 8/100 [00:00<00:09, 9.63it/s]\n 9%|▉ | 9/100 [00:00<00:09, 9.70it/s]\n 10%|█ | 10/100 [00:01<00:09, 9.75it/s]\n 11%|█ | 11/100 [00:01<00:09, 9.78it/s]\n 12%|█▏ | 12/100 [00:01<00:08, 9.82it/s]\n 13%|█▎ | 13/100 [00:01<00:08, 9.83it/s]\n 14%|█▍ | 14/100 [00:01<00:08, 9.85it/s]\n 15%|█▌ | 15/100 [00:01<00:08, 9.84it/s]\n 16%|█▌ | 16/100 [00:01<00:08, 9.84it/s]\n 17%|█▋ | 17/100 [00:01<00:08, 9.85it/s]\n 18%|█▊ | 18/100 [00:01<00:08, 9.84it/s]\n 19%|█▉ | 19/100 [00:02<00:08, 9.81it/s]\n 20%|██ | 20/100 [00:02<00:08, 9.83it/s]\n 21%|██ | 21/100 [00:02<00:08, 9.82it/s]\n 22%|██▏ | 22/100 [00:02<00:07, 9.83it/s]\n 23%|██▎ | 23/100 [00:02<00:07, 9.86it/s]\n 24%|██▍ | 24/100 [00:02<00:07, 9.87it/s]\n 25%|██▌ | 25/100 [00:02<00:07, 9.87it/s]\n 26%|██▌ | 26/100 [00:02<00:07, 9.86it/s]\n 27%|██▋ | 27/100 [00:02<00:07, 9.88it/s]\n 28%|██▊ | 28/100 [00:02<00:07, 9.89it/s]\n 29%|██▉ | 29/100 [00:03<00:07, 9.88it/s]\n 30%|███ | 30/100 [00:03<00:07, 9.88it/s]\n 31%|███ | 31/100 [00:03<00:06, 9.88it/s]\n 32%|███▏ | 32/100 [00:03<00:06, 9.86it/s]\n 33%|███▎ | 33/100 [00:03<00:06, 9.85it/s]\n 34%|███▍ | 34/100 [00:03<00:06, 9.84it/s]\n 35%|███▌ | 35/100 [00:03<00:06, 9.86it/s]\n 36%|███▌ | 36/100 [00:03<00:06, 9.87it/s]\n 37%|███▋ | 37/100 [00:03<00:06, 9.88it/s]\n 38%|███▊ | 38/100 [00:03<00:06, 9.88it/s]\n 39%|███▉ | 39/100 [00:04<00:06, 9.87it/s]\n 40%|████ | 40/100 [00:04<00:06, 9.86it/s]\n 41%|████ | 41/100 [00:04<00:05, 9.83it/s]\n 42%|████▏ | 42/100 [00:04<00:05, 9.82it/s]\n 43%|████▎ | 43/100 [00:04<00:05, 9.80it/s]\n 44%|████▍ | 44/100 [00:04<00:05, 9.78it/s]\n 45%|████▌ | 45/100 [00:04<00:05, 9.81it/s]\n 46%|████▌ | 46/100 [00:04<00:05, 9.82it/s]\n 47%|████▋ | 47/100 [00:04<00:05, 9.87it/s]\n 48%|████▊ | 48/100 [00:04<00:05, 9.89it/s]\n 49%|████▉ | 49/100 [00:05<00:05, 9.90it/s]\n 50%|█████ | 50/100 [00:05<00:05, 9.91it/s]\n 51%|█████ | 51/100 [00:05<00:04, 9.91it/s]\n 52%|█████▏ | 52/100 [00:05<00:04, 9.91it/s]\n 53%|█████▎ | 53/100 [00:05<00:04, 9.91it/s]\n 54%|█████▍ | 54/100 [00:05<00:04, 9.93it/s]\n 55%|█████▌ | 55/100 [00:05<00:04, 9.93it/s]\n 56%|█████▌ | 56/100 [00:05<00:04, 9.94it/s]\n 57%|█████▋ | 57/100 [00:05<00:04, 9.94it/s]\n 58%|█████▊ | 58/100 [00:05<00:04, 9.94it/s]\n 59%|█████▉ | 59/100 [00:06<00:04, 9.94it/s]\n 60%|██████ | 60/100 [00:06<00:04, 9.94it/s]\n 61%|██████ | 61/100 [00:06<00:03, 9.93it/s]\n 62%|██████▏ | 62/100 [00:06<00:03, 9.94it/s]\n 63%|██████▎ | 63/100 [00:06<00:03, 9.95it/s]\n 64%|██████▍ | 64/100 [00:06<00:03, 9.94it/s]\n 65%|██████▌ | 65/100 [00:06<00:03, 9.92it/s]\n 66%|██████▌ | 66/100 [00:06<00:03, 9.93it/s]\n 67%|██████▋ | 67/100 [00:06<00:03, 9.93it/s]\n 68%|██████▊ | 68/100 [00:06<00:03, 9.93it/s]\n 69%|██████▉ | 69/100 [00:07<00:03, 9.95it/s]\n 70%|███████ | 70/100 [00:07<00:03, 9.95it/s]\n 71%|███████ | 71/100 [00:07<00:02, 9.95it/s]\n 72%|███████▏ | 72/100 [00:07<00:02, 9.94it/s]\n 73%|███████▎ | 73/100 [00:07<00:02, 9.93it/s]\n 75%|███████▌ | 75/100 [00:07<00:02, 9.97it/s]\n 77%|███████▋ | 77/100 [00:07<00:02, 9.99it/s]\n 79%|███████▉ | 79/100 [00:08<00:02, 10.00it/s]\n 80%|████████ | 80/100 [00:08<00:01, 10.00it/s]\n 81%|████████ | 81/100 [00:08<00:01, 9.98it/s]\n 83%|████████▎ | 83/100 [00:08<00:01, 9.98it/s]\n 84%|████████▍ | 84/100 [00:08<00:01, 9.96it/s]\n 86%|████████▌ | 86/100 [00:08<00:01, 9.97it/s]\n 88%|████████▊ | 88/100 [00:08<00:01, 9.97it/s]\n 89%|████████▉ | 89/100 [00:09<00:01, 9.94it/s]\n 90%|█████████ | 90/100 [00:09<00:01, 9.93it/s]\n 91%|█████████ | 91/100 [00:09<00:00, 9.94it/s]\n 92%|█████████▏| 92/100 [00:09<00:00, 9.93it/s]\n 93%|█████████▎| 93/100 [00:09<00:00, 9.94it/s]\n 95%|█████████▌| 95/100 [00:09<00:00, 9.94it/s]\n 96%|█████████▌| 96/100 [00:09<00:00, 9.94it/s]\n 98%|█████████▊| 98/100 [00:09<00:00, 9.99it/s]/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torchsde/_brownian/brownian_interval.py:599: UserWarning: Should have ta>=t0 but got ta=0.029999999329447746 and t0=0.03.\nwarnings.warn(f\"Should have ta>=t0 but got ta={ta} and t0={self._start}.\")\n100%|██████████| 100/100 [00:10<00:00, 10.10it/s]\n100%|██████████| 100/100 [00:10<00:00, 9.83it/s]\nffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers\nbuilt with gcc 11 (Ubuntu 11.2.0-19ubuntu1)\nconfiguration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared\nlibavutil 56. 70.100 / 56. 70.100\nlibavcodec 58.134.100 / 58.134.100\nlibavformat 58. 76.100 / 58. 76.100\nlibavdevice 58. 13.100 / 58. 13.100\nlibavfilter 7.110.100 / 7.110.100\nlibswscale 5. 9.100 / 5. 9.100\nlibswresample 3. 9.100 / 3. 9.100\nlibpostproc 55. 9.100 / 55. 9.100\nGuessed Channel Layout for Input Stream #0.0 : stereo\nInput #0, wav, from 'output.wav':\nMetadata:\nencoder : Lavf58.76.100\nDuration: 00:01:00.98, bitrate: 1411 kb/s\nStream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 44100 Hz, stereo, s16, 1411 kb/s\nStream mapping:\nStream #0:0 -> #0:0 (pcm_s16le (native) -> mp3 (libmp3lame))\nPress [q] to stop, [?] for help\nOutput #0, mp3, to 'output.mp3':\nMetadata:\nTSSE : Lavf58.76.100\nStream #0:0: Audio: mp3, 44100 Hz, stereo, s16p\nMetadata:\nencoder : Lavc58.134.100 libmp3lame\nsize= 0kB time=00:00:00.00 bitrate=N/A speed=N/A\nsize= 512kB time=00:00:33.72 bitrate= 124.4kbits/s speed=67.4x\nsize= 954kB time=00:01:00.97 bitrate= 128.1kbits/s speed=76.4x\nvideo:0kB audio:953kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.025913%\nSuccess: {'message': 'Song state with id 10001 updated successfully'}",
"metrics": {
"predict_time": 15.780399997,
"total_time": 63.977407
},
"output": {
"output": "https://storage.googleapis.com/lagoe_prod_generated_songs/10001/10001.mp3"
},
"started_at": "2024-10-16T00:07:31.741007Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/5z7whv7rb1rgg0cjjajtny239m",
"cancel": "https://api.replicate.com/v1/predictions/5z7whv7rb1rgg0cjjajtny239m/cancel"
},
"version": "4a98a2079e2e0cd380582ba8b159e943664135b721db6bbf1eefdffbdebba2d1"
}Generated in
Prompt: acoustic guitar
2228991867
/src/stable_audio_tools/models/conditioners.py:314: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead.
with torch.cuda.amp.autocast(dtype=torch.float16) and torch.set_grad_enabled(self.enable_grad):
/src/stable_audio_tools/inference/sampling.py:177: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead.
with torch.cuda.amp.autocast():
0%| | 0/100 [00:00<?, ?it/s]/root/.pyenv/versions/3.10.14/lib/python3.10/contextlib.py:103: FutureWarning: `torch.backends.cuda.sdp_kernel()` is deprecated. In the future, this context manager will be removed. Please see `torch.nn.attention.sdpa_kernel()` for the new context manager, with updated signature.
self.gen = func(*args, **kwds)
1%| | 1/100 [00:00<00:18, 5.39it/s]
2%|▏ | 2/100 [00:00<00:13, 7.33it/s]
3%|▎ | 3/100 [00:00<00:11, 8.28it/s]
4%|▍ | 4/100 [00:00<00:10, 8.84it/s]
5%|▌ | 5/100 [00:00<00:10, 9.17it/s]
6%|▌ | 6/100 [00:00<00:10, 9.39it/s]
7%|▋ | 7/100 [00:00<00:09, 9.54it/s]
8%|▊ | 8/100 [00:00<00:09, 9.63it/s]
9%|▉ | 9/100 [00:00<00:09, 9.70it/s]
10%|█ | 10/100 [00:01<00:09, 9.75it/s]
11%|█ | 11/100 [00:01<00:09, 9.78it/s]
12%|█▏ | 12/100 [00:01<00:08, 9.82it/s]
13%|█▎ | 13/100 [00:01<00:08, 9.83it/s]
14%|█▍ | 14/100 [00:01<00:08, 9.85it/s]
15%|█▌ | 15/100 [00:01<00:08, 9.84it/s]
16%|█▌ | 16/100 [00:01<00:08, 9.84it/s]
17%|█▋ | 17/100 [00:01<00:08, 9.85it/s]
18%|█▊ | 18/100 [00:01<00:08, 9.84it/s]
19%|█▉ | 19/100 [00:02<00:08, 9.81it/s]
20%|██ | 20/100 [00:02<00:08, 9.83it/s]
21%|██ | 21/100 [00:02<00:08, 9.82it/s]
22%|██▏ | 22/100 [00:02<00:07, 9.83it/s]
23%|██▎ | 23/100 [00:02<00:07, 9.86it/s]
24%|██▍ | 24/100 [00:02<00:07, 9.87it/s]
25%|██▌ | 25/100 [00:02<00:07, 9.87it/s]
26%|██▌ | 26/100 [00:02<00:07, 9.86it/s]
27%|██▋ | 27/100 [00:02<00:07, 9.88it/s]
28%|██▊ | 28/100 [00:02<00:07, 9.89it/s]
29%|██▉ | 29/100 [00:03<00:07, 9.88it/s]
30%|███ | 30/100 [00:03<00:07, 9.88it/s]
31%|███ | 31/100 [00:03<00:06, 9.88it/s]
32%|███▏ | 32/100 [00:03<00:06, 9.86it/s]
33%|███▎ | 33/100 [00:03<00:06, 9.85it/s]
34%|███▍ | 34/100 [00:03<00:06, 9.84it/s]
35%|███▌ | 35/100 [00:03<00:06, 9.86it/s]
36%|███▌ | 36/100 [00:03<00:06, 9.87it/s]
37%|███▋ | 37/100 [00:03<00:06, 9.88it/s]
38%|███▊ | 38/100 [00:03<00:06, 9.88it/s]
39%|███▉ | 39/100 [00:04<00:06, 9.87it/s]
40%|████ | 40/100 [00:04<00:06, 9.86it/s]
41%|████ | 41/100 [00:04<00:05, 9.83it/s]
42%|████▏ | 42/100 [00:04<00:05, 9.82it/s]
43%|████▎ | 43/100 [00:04<00:05, 9.80it/s]
44%|████▍ | 44/100 [00:04<00:05, 9.78it/s]
45%|████▌ | 45/100 [00:04<00:05, 9.81it/s]
46%|████▌ | 46/100 [00:04<00:05, 9.82it/s]
47%|████▋ | 47/100 [00:04<00:05, 9.87it/s]
48%|████▊ | 48/100 [00:04<00:05, 9.89it/s]
49%|████▉ | 49/100 [00:05<00:05, 9.90it/s]
50%|█████ | 50/100 [00:05<00:05, 9.91it/s]
51%|█████ | 51/100 [00:05<00:04, 9.91it/s]
52%|█████▏ | 52/100 [00:05<00:04, 9.91it/s]
53%|█████▎ | 53/100 [00:05<00:04, 9.91it/s]
54%|█████▍ | 54/100 [00:05<00:04, 9.93it/s]
55%|█████▌ | 55/100 [00:05<00:04, 9.93it/s]
56%|█████▌ | 56/100 [00:05<00:04, 9.94it/s]
57%|█████▋ | 57/100 [00:05<00:04, 9.94it/s]
58%|█████▊ | 58/100 [00:05<00:04, 9.94it/s]
59%|█████▉ | 59/100 [00:06<00:04, 9.94it/s]
60%|██████ | 60/100 [00:06<00:04, 9.94it/s]
61%|██████ | 61/100 [00:06<00:03, 9.93it/s]
62%|██████▏ | 62/100 [00:06<00:03, 9.94it/s]
63%|██████▎ | 63/100 [00:06<00:03, 9.95it/s]
64%|██████▍ | 64/100 [00:06<00:03, 9.94it/s]
65%|██████▌ | 65/100 [00:06<00:03, 9.92it/s]
66%|██████▌ | 66/100 [00:06<00:03, 9.93it/s]
67%|██████▋ | 67/100 [00:06<00:03, 9.93it/s]
68%|██████▊ | 68/100 [00:06<00:03, 9.93it/s]
69%|██████▉ | 69/100 [00:07<00:03, 9.95it/s]
70%|███████ | 70/100 [00:07<00:03, 9.95it/s]
71%|███████ | 71/100 [00:07<00:02, 9.95it/s]
72%|███████▏ | 72/100 [00:07<00:02, 9.94it/s]
73%|███████▎ | 73/100 [00:07<00:02, 9.93it/s]
75%|███████▌ | 75/100 [00:07<00:02, 9.97it/s]
77%|███████▋ | 77/100 [00:07<00:02, 9.99it/s]
79%|███████▉ | 79/100 [00:08<00:02, 10.00it/s]
80%|████████ | 80/100 [00:08<00:01, 10.00it/s]
81%|████████ | 81/100 [00:08<00:01, 9.98it/s]
83%|████████▎ | 83/100 [00:08<00:01, 9.98it/s]
84%|████████▍ | 84/100 [00:08<00:01, 9.96it/s]
86%|████████▌ | 86/100 [00:08<00:01, 9.97it/s]
88%|████████▊ | 88/100 [00:08<00:01, 9.97it/s]
89%|████████▉ | 89/100 [00:09<00:01, 9.94it/s]
90%|█████████ | 90/100 [00:09<00:01, 9.93it/s]
91%|█████████ | 91/100 [00:09<00:00, 9.94it/s]
92%|█████████▏| 92/100 [00:09<00:00, 9.93it/s]
93%|█████████▎| 93/100 [00:09<00:00, 9.94it/s]
95%|█████████▌| 95/100 [00:09<00:00, 9.94it/s]
96%|█████████▌| 96/100 [00:09<00:00, 9.94it/s]
98%|█████████▊| 98/100 [00:09<00:00, 9.99it/s]/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torchsde/_brownian/brownian_interval.py:599: UserWarning: Should have ta>=t0 but got ta=0.029999999329447746 and t0=0.03.
warnings.warn(f"Should have ta>=t0 but got ta={ta} and t0={self._start}.")
100%|██████████| 100/100 [00:10<00:00, 10.10it/s]
100%|██████████| 100/100 [00:10<00:00, 9.83it/s]
ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers
built with gcc 11 (Ubuntu 11.2.0-19ubuntu1)
configuration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
libavutil 56. 70.100 / 56. 70.100
libavcodec 58.134.100 / 58.134.100
libavformat 58. 76.100 / 58. 76.100
libavdevice 58. 13.100 / 58. 13.100
libavfilter 7.110.100 / 7.110.100
libswscale 5. 9.100 / 5. 9.100
libswresample 3. 9.100 / 3. 9.100
libpostproc 55. 9.100 / 55. 9.100
Guessed Channel Layout for Input Stream #0.0 : stereo
Input #0, wav, from 'output.wav':
Metadata:
encoder : Lavf58.76.100
Duration: 00:01:00.98, bitrate: 1411 kb/s
Stream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 44100 Hz, stereo, s16, 1411 kb/s
Stream mapping:
Stream #0:0 -> #0:0 (pcm_s16le (native) -> mp3 (libmp3lame))
Press [q] to stop, [?] for help
Output #0, mp3, to 'output.mp3':
Metadata:
TSSE : Lavf58.76.100
Stream #0:0: Audio: mp3, 44100 Hz, stereo, s16p
Metadata:
encoder : Lavc58.134.100 libmp3lame
size= 0kB time=00:00:00.00 bitrate=N/A speed=N/A
size= 512kB time=00:00:33.72 bitrate= 124.4kbits/s speed=67.4x
size= 954kB time=00:01:00.97 bitrate= 128.1kbits/s speed=76.4x
video:0kB audio:953kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.025913%
Success: {'message': 'Song state with id 10001 updated successfully'}This output was created using a different version of the model, ardianfe/stable-audio-2:4a98a207.
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.