Instructions to use PsiPi/audio with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Stable Audio Tools
How to use PsiPi/audio with Stable Audio Tools:
import torch import torchaudio from einops import rearrange from stable_audio_tools import get_pretrained_model from stable_audio_tools.inference.generation import generate_diffusion_cond device = "cuda" if torch.cuda.is_available() else "cpu" # Download model model, model_config = get_pretrained_model("PsiPi/audio") sample_rate = model_config["sample_rate"] sample_size = model_config["sample_size"] model = model.to(device) # Set up text and timing conditioning conditioning = [{ "prompt": "128 BPM tech house drum loop", }] # Generate stereo audio output = generate_diffusion_cond( model, conditioning=conditioning, sample_size=sample_size, device=device ) # Rearrange audio batch to a single sequence output = rearrange(output, "b d n -> d (b n)") # Peak normalize, clip, convert to int16, and save to file output = output.to(torch.float32).div(torch.max(torch.abs(output))).clamp(-1, 1).mul(32767).to(torch.int16).cpu() torchaudio.save("output.wav", output, sample_rate) - Notebooks
- Google Colab
- Kaggle
| { | |
| "additional_special_tokens": [ | |
| "<extra_id_0>", | |
| "<extra_id_1>", | |
| "<extra_id_2>", | |
| "<extra_id_3>", | |
| "<extra_id_4>", | |
| "<extra_id_5>", | |
| "<extra_id_6>", | |
| "<extra_id_7>", | |
| "<extra_id_8>", | |
| "<extra_id_9>", | |
| "<extra_id_10>", | |
| "<extra_id_11>", | |
| "<extra_id_12>", | |
| "<extra_id_13>", | |
| "<extra_id_14>", | |
| "<extra_id_15>", | |
| "<extra_id_16>", | |
| "<extra_id_17>", | |
| "<extra_id_18>", | |
| "<extra_id_19>", | |
| "<extra_id_20>", | |
| "<extra_id_21>", | |
| "<extra_id_22>", | |
| "<extra_id_23>", | |
| "<extra_id_24>", | |
| "<extra_id_25>", | |
| "<extra_id_26>", | |
| "<extra_id_27>", | |
| "<extra_id_28>", | |
| "<extra_id_29>", | |
| "<extra_id_30>", | |
| "<extra_id_31>", | |
| "<extra_id_32>", | |
| "<extra_id_33>", | |
| "<extra_id_34>", | |
| "<extra_id_35>", | |
| "<extra_id_36>", | |
| "<extra_id_37>", | |
| "<extra_id_38>", | |
| "<extra_id_39>", | |
| "<extra_id_40>", | |
| "<extra_id_41>", | |
| "<extra_id_42>", | |
| "<extra_id_43>", | |
| "<extra_id_44>", | |
| "<extra_id_45>", | |
| "<extra_id_46>", | |
| "<extra_id_47>", | |
| "<extra_id_48>", | |
| "<extra_id_49>", | |
| "<extra_id_50>", | |
| "<extra_id_51>", | |
| "<extra_id_52>", | |
| "<extra_id_53>", | |
| "<extra_id_54>", | |
| "<extra_id_55>", | |
| "<extra_id_56>", | |
| "<extra_id_57>", | |
| "<extra_id_58>", | |
| "<extra_id_59>", | |
| "<extra_id_60>", | |
| "<extra_id_61>", | |
| "<extra_id_62>", | |
| "<extra_id_63>", | |
| "<extra_id_64>", | |
| "<extra_id_65>", | |
| "<extra_id_66>", | |
| "<extra_id_67>", | |
| "<extra_id_68>", | |
| "<extra_id_69>", | |
| "<extra_id_70>", | |
| "<extra_id_71>", | |
| "<extra_id_72>", | |
| "<extra_id_73>", | |
| "<extra_id_74>", | |
| "<extra_id_75>", | |
| "<extra_id_76>", | |
| "<extra_id_77>", | |
| "<extra_id_78>", | |
| "<extra_id_79>", | |
| "<extra_id_80>", | |
| "<extra_id_81>", | |
| "<extra_id_82>", | |
| "<extra_id_83>", | |
| "<extra_id_84>", | |
| "<extra_id_85>", | |
| "<extra_id_86>", | |
| "<extra_id_87>", | |
| "<extra_id_88>", | |
| "<extra_id_89>", | |
| "<extra_id_90>", | |
| "<extra_id_91>", | |
| "<extra_id_92>", | |
| "<extra_id_93>", | |
| "<extra_id_94>", | |
| "<extra_id_95>", | |
| "<extra_id_96>", | |
| "<extra_id_97>", | |
| "<extra_id_98>", | |
| "<extra_id_99>" | |
| ], | |
| "eos_token": "</s>", | |
| "pad_token": "<pad>", | |
| "unk_token": "<unk>" | |
| } | |