ardianfe/stable-audio-2 📝🔢❓ → ❓

▶️ 8.5K runs 📅 Oct 2024 ⚙️ Cog 0.9.12 🔗 GitHub ⚖️ License

music-generation text-to-audio

About

music generation with fine tuned stable audio

Example Output

Prompt:

"acoustic guitar"

Output

{"output":"https://storage.googleapis.com/lagoe_prod_generated_songs/10001/10001.mp3"}

Performance Metrics

15.78s Prediction Time

63.98s Total Time

All Input Parameters

{
  "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
}

Input Parameters

key (required) Type: string: key password
seed Type: integerDefault: -1
steps Type: integerDefault: 100
prompt (required) Type: string
song_id (required) Type: integer: song id to store to GCS
cfg_scale Type: numberDefault: 6
sigma_max Type: integerDefault: 500
sigma_min Type: numberDefault: 0.03
batch_size Type: integerDefault: 1
sampler_type Type: stringDefault: dpmpp-3m-sde
output_format Default: mp3: Output format for generated audio.
seconds_start Type: integerDefault: 0
seconds_total Type: integerDefault: 8Range: ∞ - 90
negative_prompt Type: stringDefault:
init_noise_level Type: numberDefault: 1

Output Schema

Output

Type: object

Example Execution Logs

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'}

Version Details

Version ID: 6761efad154cb36efc2b10bb5432b561e3ce2557130557b34f9fd4874a894c84
Version Created: November 25, 2024

Run on Replicate →