MCPcopy Create free account

hub / github.com/Stability-AI/stable-audio-tools / functions

Functions1,182 in github.com/Stability-AI/stable-audio-tools

⨍ Functions 1,182◇ Types & classes 277
Method__init__
(self, model_config)
train.py:24
Method__init__
( self, model, output_path, is_discrete=False, model_half=False,
pre_encode.py:40
Method__init__
(self, n_samples: int, sample_rate: int, randomize: bool = True, pad: bool = True)
stable_audio_tools/data/utils.py:26
Method__init__
(self, p=0.5)
stable_audio_tools/data/utils.py:129
Method__init__
(self, params=[-16, 2], sample_rate=16000, energy_threshold=1e-6)
stable_audio_tools/data/utils.py:155
Method__init__
( self, id: str, path: str, keywords: Optional[List[str]]=None, custom
stable_audio_tools/data/dataset.py:159
Method__init__
( self, latent_extension: str = "npy", filelist_path = None, *args, **
stable_audio_tools/data/dataset.py:176
Method__init__
( self, configs: List[LatentDatasetConfig], latent_crop_length=None, min_lengt
stable_audio_tools/data/dataset.py:325
Method__init__
( self, id: str, s3_path: str, custom_metadata_fn: Optional[Callable[[str], st
stable_audio_tools/data/dataset.py:692
Method__init__
( self, id: str, path: str, custom_metadata_fn: Optional[Callable[[str], str]]
stable_audio_tools/data/dataset.py:716
Method__init__
( self, datasets: List[S3DatasetConfig], batch_size, sample_size, samp
stable_audio_tools/data/dataset.py:772
Method__init__
(self, min_length=256, max_length=4096, alpha_min=1.0, alpha_max=1.0)
stable_audio_tools/inference/sampling.py:62
Method__init__
(self, base_shift=0.5, max_shift=1.15, max_length=4096, min_length=256, use_sine=False)
stable_audio_tools/inference/sampling.py:114
Method__init__
(self, anchor_length=2000, anchor_logsnr=-6.2, rate=1.0, logsnr_end=2.0)
stable_audio_tools/inference/sampling.py:179
Method__init__
(self, inner_model)
stable_audio_tools/inference/k_diffusion/external.py:14
Method__init__
(self, x, t0, t1, seed=None, **kwargs)
stable_audio_tools/inference/k_diffusion/sampling.py:49
Method__init__
(self, x, sigma_min, sigma_max, seed=None, transform=lambda x: x)
stable_audio_tools/inference/k_diffusion/sampling.py:88
Method__init__
(self, h, pcoeff, icoeff, dcoeff, order=1, accept_safety=0.81, eps=1e-8)
stable_audio_tools/inference/k_diffusion/sampling.py:193
Method__init__
(self, model, extra_args=None, eps_callback=None, info_callback=None)
stable_audio_tools/inference/k_diffusion/sampling.py:223
Method__init__
( self, params: Iterable[nn.parameter.Parameter], lr: float = 1e-3, betas: Tup
stable_audio_tools/training/optims.py:33
Method__init__
( self, params, muon_lr: float = 0.02, muon_momentum: float = 0.95, mu
stable_audio_tools/training/optims.py:250
Method__init__
( self, model: ConditionedDiffusionModelWrapper, arc_config: dict,
stable_audio_tools/training/arc.py:97
Method__init__
( self, model, ema_model = None, # if your model has lazylinears or other ty
stable_audio_tools/training/ema.py:41
Method__init__
(self, optimizer, inv_gamma=1., power=1., warmup=0., final_lr=0., last_epoch=-1)
stable_audio_tools/training/utils.py:37
Method__init__
(self, every_n_steps: int = 10)
stable_audio_tools/training/utils.py:199
Method__init__
( self, model: DiffusionModelWrapper, lr: float = 1e-4, pre_en
stable_audio_tools/training/diffusion.py:59
Method__init__
(self, demo_every=2000, num_demos=8, demo_steps=250,
stable_audio_tools/training/diffusion.py:201
Method__init__
( self, model: ConditionedDiffusionModelWrapper, lr: float = None,
stable_audio_tools/training/diffusion.py:273
Method__init__
(self, demo_every=2000, num_demos=8, sample_size=65536,
stable_audio_tools/training/diffusion.py:946
Method__init__
( self, demo_every=2000, demo_steps=250, sample_size=65536, sample_rat
stable_audio_tools/training/diffusion.py:1238
Method__init__
( self, model: DiffusionAutoencoder, lr: float = 1e-4, ema_cop
stable_audio_tools/training/diffusion.py:1742
Method__init__
( self, demo_dl, demo_every=2000, demo_steps=250, sample_size=65536,
stable_audio_tools/training/diffusion.py:1906
Method__init__
(self, fsdp_config)
stable_audio_tools/training/fsdp.py:251
Method__init__
( self, autoencoder: AudioAutoencoder, sample_rate=48000, loss
stable_audio_tools/training/autoencoders.py:227
Method__init__
(self, demo_every: int = 1000, demo_dl = None)
stable_audio_tools/training/clap.py:470
Method__init__
( self, model: AudioLanguageModelWrapper, lr = 1e-4, use_em
stable_audio_tools/training/lm.py:22
Method__init__
( self, demo_every: int = 2000, conditioner_types: tp.Optional[tp.Tuple[str, ...]] = N
stable_audio_tools/training/metrics/conditioner_distance.py:32
Method__init__
(self, in_channels, out_channels)
stable_audio_tools/training/metrics/fad_metrics.py:218
Method__init__
( self, metrics_every=1000, cfg_scale=7, sampling_steps=50, num_genera
stable_audio_tools/training/metrics/fad_metrics.py:837
Method__init__
( self, metrics_every=1000, ref_audios_path=False, ref_audios_ext='.wav',
stable_audio_tools/training/metrics/fad_metrics.py:1181
Method__init__
(self, init_val = 1.0)
stable_audio_tools/training/losses/utils.py:8
Method__init__
(self, name: str, weight: float = 1.0, decay = 1.0)
stable_audio_tools/training/losses/losses.py:11
Method__init__
(self, key: str, name, weight: float = 1.0, decay = 1.0)
stable_audio_tools/training/losses/losses.py:29
Method__init__
(self, key: str, target: float, name: str, weight: float = 1.0)
stable_audio_tools/training/losses/losses.py:39
Method__init__
(self, key_a: str, key_b: str, weight: float = 1.0, mask_key: str = None, name: str = 'mse_loss',decay = 1.0)
stable_audio_tools/training/losses/losses.py:69
Method__init__
(self, loss_module, input_key: str, target_key: str, name: str, weight: float = 1, decay = 1.0)
stable_audio_tools/training/losses/losses.py:96
Method__init__
(self, loss_module, input_key: str, target_key: str, name: str, weight: float = 1, decay = 1.0)
stable_audio_tools/training/losses/losses.py:110
Method__init__
(self, losses: tp.List[LossModule])
stable_audio_tools/training/losses/losses.py:118
Method__init__
(self, key_a: str, key_b: str, weight: float = 1.0, mask_key: str = None, name: str = 'stereo_image_loss', dec
stable_audio_tools/training/losses/losses.py:139
Method__init__
(self, key_a: str, key_b: str, weight: float = 1.0, name: str = 'time_domain_mmd_loss', decay = 1.0)
stable_audio_tools/training/losses/losses.py:158
Method__init__
Initialize sum and difference extraction module.
stable_audio_tools/training/losses/auraloss.py:77
Method__init__
(self, filter_type="kw", coef=0.85, fs=44100, ntaps=257, pad_mode: str = "reflect", ref_hz: f
stable_audio_tools/training/losses/auraloss.py:117
Method__init__
(self, eps=1e-4)
stable_audio_tools/training/losses/auraloss.py:238
Method__init__
(self, log=True, log_eps=0.0, log_fac=1.0, distance="L1", reduction="mean")
stable_audio_tools/training/losses/auraloss.py:274
Method__init__
(self, log_eps=0.0, log_fac=1.0, reduction="mean")
stable_audio_tools/training/losses/auraloss.py:300
Method__init__
( self, fft_sizes: List[int] = [1024, 2048, 512], hop_sizes: List[int] = [120, 240, 50
stable_audio_tools/training/losses/auraloss.py:588
Method__init__
( self, fft_sizes: List[int], hop_sizes: List[int], win_lengths: List[int],
stable_audio_tools/training/losses/auraloss.py:679
Method__init__
(self, zero_mean=True, eps=1e-8, reduction="mean")
stable_audio_tools/training/losses/auraloss.py:752
Method__init__
(self, zero_mean=True, eps=1e-8, reduction="mean")
stable_audio_tools/training/losses/auraloss.py:795
Method__init__
( self, sample_rate, fft_size=1024, hop_size=256, win_length=1024,
stable_audio_tools/training/losses/auraloss.py:821
Method__init__
(self, feature_ids: tp.Optional[tp.List[int]] = None, weight: float = 1.0, model_name:
stable_audio_tools/training/losses/semantic.py:16
Method__init__
(self, sample_rate: int, n_mels: tp.List[int], window_lengths: tp.List[int], loss_fn:
stable_audio_tools/training/losses/semantic.py:216
Method__init__
(self, latent_dim, transformer_dim, depth, mask_rate = 0.4, mask_block_size = 8, dyt = True, *args, **kwargs)
stable_audio_tools/models/discriminators.py:65
Method__init__
(self, audio_dim, latent_dim, text_dim = None, transformer_dim = 512, depth = 4, seq_mask_rate = 0.4, feature_
stable_audio_tools/models/discriminators.py:99
Method__init__
(self, normalize_losses=False, loss_type: tp.Literal["hinge", "rpgan"]="hinge", *args, **kwargs)
stable_audio_tools/models/discriminators.py:222
Method__init__
( self, in_size: int, convolution: tp.Union[nn.Conv1d, nn.Conv2d], out_size: i
stable_audio_tools/models/discriminators.py:272
Method__init__
(self, in_channels: int, n_scales: int, **conv_kwargs)
stable_audio_tools/models/discriminators.py:327
Method__init__
(self, in_channels: int, periods: tp.Sequence[int], **conv_
stable_audio_tools/models/discriminators.py:349
Method__init__
(self, discriminator_list: tp.Sequence[nn.Module], keys: tp.Sequence[str])
stable_audio_tools/models/discriminators.py:384
Method__init__
( self, in_channels=1, )
stable_audio_tools/models/discriminators.py:450
Method__init__
(self, rate: int = 1, sample_rate: int = 44100, channels=1)
stable_audio_tools/models/discriminators.py:554
Method__init__
Complex multi-band spectrogram discriminator. Parameters ---------- window_length : int Window length of STFT.
stable_audio_tools/models/discriminators.py:593
Method__init__
(self, cfg: dict, hop_length: int, n_octaves:int, bins_per_octave: int)
stable_audio_tools/models/discriminators.py:675
Method__init__
(self, cfg: dict)
stable_audio_tools/models/discriminators.py:818
Method__init__
Discriminator that combines multiple discriminators. Parameters ---------- rates : list, optional sampling rates
stable_audio_tools/models/discriminators.py:903
Method__init__
(self, use_hinge: bool = False, **discriminator_kwargs)
stable_audio_tools/models/discriminators.py:956
Method__init__
(self, sample_rate: int, channels: int = 1, use_hinge: bool = False, periods: List[int
stable_audio_tools/models/discriminators.py:1014
Method__init__
( self, period: int, taps: int = 0, beta: float = 0.0, cutoff_freq: fl
stable_audio_tools/models/discriminators.py:1041
Method__init__
( self, n_chroma: int, sample_rate: int, kernel_sizes: tp.List[int] = [5, 5, 5
stable_audio_tools/models/discriminators.py:1109
Method__init__
( self, periods: tp.List[int] = [1, 2, 3, 5, 7, 11], taps: int = 256, beta: fl
stable_audio_tools/models/discriminators.py:1170
Method__init__
(self, normalize_losses = False, loss_type: tp.Literal["hinge", "rpgan", "sigmoid_rpgan"]="rpgan", add_noise =
stable_audio_tools/models/discriminators.py:1205
Method__init__
(self, normalize_losses = False, loss_type: tp.Literal["hinge", "rpgan", "sigmoid_rpgan"]="rpgan", add_noise =
stable_audio_tools/models/discriminators.py:1285
Method__init__
(self, in_dim, transformer_dim, stride, pretransform, sliding_window = [1,1], depth = 3, checkpointing = False
stable_audio_tools/models/discriminators.py:1383
Method__init__
(self, in_channels: int = 1, n_ffts: tp.List[int] = [4096, 1024, 128], depths: tp.List[int] = [3, 3, 3], strid
stable_audio_tools/models/discriminators.py:1409
Method__init__
(self, in_channels: int = 1, patch_sizes: tp.List[int] = [29, 443, 953], depths: tp.List[int] = [3, 3, 3], str
stable_audio_tools/models/discriminators.py:1433
Method__init__
(self, in_channels: int = 1, levels: tp.List[int] = [4, 8, 10], depths: tp.List[int] = [3, 3, 3], strides: tp.
stable_audio_tools/models/discriminators.py:1458
Method__init__
(self, in_channels: int, n_chroma: int = 64, sample_rate: int = 44100, n_fft: int = 4096, ctroct: float = 5.0,
stable_audio_tools/models/discriminators.py:1482
Method__init__
(self, in_channels: int = 1, centres: tp.List[int] = [1.0, 5.0, 9.0], octwidths: tp.List[int] = [1.0, 1.5, 1.0
stable_audio_tools/models/discriminators.py:1499
Method__init__
(self, channels)
stable_audio_tools/models/discriminators.py:1571
Method__init__
(self, loss_type="lsgan", *args, **kwargs)
stable_audio_tools/models/arc.py:79
Method__init__
(self, channels, dilation)
stable_audio_tools/models/arc.py:118
Method__init__
(self, channels, hidden_dim=64, loss_type="lsgan", dilations=[1, 2, 4, 1, 2, 4])
stable_audio_tools/models/arc.py:134
Method__init__
( self, channels, hidden_dim=256, depth=4, dim_heads=64, slidi
stable_audio_tools/models/arc.py:205
Method__init__
( self, channels, heads=None, hidden_dim=256, depth=3, dim_hea
stable_audio_tools/models/arc.py:302
Method__init__
(self, attenuation, num_bands)
stable_audio_tools/models/pqmf.py:19
Method__init__
(self, in_channels, out_channels, dilation, use_snake=False, antialias_activation=False, depthwise = False, bi
stable_audio_tools/models/blocks.py:43
Method__init__
(self, main, skip=None)
stable_audio_tools/models/blocks.py:65
Method__init__
(self, c_in, c_mid, c_out, is_last=False, kernel_size=5, conv_bias=True)
stable_audio_tools/models/blocks.py:74
Method__init__
(self, c_in, n_head=1, dropout_rate=0.)
stable_audio_tools/models/blocks.py:86
Method__init__
(self, *main)
stable_audio_tools/models/blocks.py:128
← previousnext →501–600 of 1,182, ranked by callers