(element, obj)

(y)

()

()

(c)

(c)

(t, x)

(self, wav)

(self, x, scale=1000)

(self, x: float["b n d"], mask: bool["b n"] | None = None)

(self, x)

(self, x: torch.Tensor)

(self, x, emb=None)

(self, x, emb)

(self, x)

( self, x: float["b n d"], # noised input x # noqa: F722 c: float["b n d"] = None,

(self, x, t, mask=None, rope=None)

(self, x, c, t, mask=None, rope=None, c_rope=None)

(self, timestep: float["b"])

(self, text: int["b nt"], drop_text=False)

(self, x: float["b n d"], cond: float["b n d"], drop_audio_cond=False)

( self, x: float["b n d"], # nosied input audio # noqa: F722 cond: float["b n d"],

(self, text: int["b nt"], seq_len, drop_text=False)

(self, x: float["b n d"], cond: float["b n d"], text_embed: float["b n d"], drop_audio_cond=False)

( self, x: float["b n d"], # nosied input audio # noqa: F722 cond: float["b n d"],

(self, text: int["b nt"], seq_len, drop_text=False)

(self, x: float["b n d"], cond: float["b n d"], text_embed: float["b n d"], drop_audio_cond=False)

( self, x: float["b n d"], # nosied input audio # noqa: F722 cond: float["b n d"],

(node)

( waveform, n_fft=1024, n_mel_channels=100, target_sample_rate=24000, hop_length=256,

( waveform, n_fft=1024, n_mel_channels=100, target_sample_rate=24000, hop_length=256,

(c)

(element)

(elements)

(c)

(c)

(unknown)

(unknown)

(unknown)

(element, html)

(unknown)

(unknown)

()

(unknown)

(unknown)

()

(t,e)

(params, opt)

(c)

(element)

(element)

(element)

(scp, path_list,test=-1, split_token=" ")

(element)

(c)

(element, classes)

(elements)

()

()

(element)

(target_list, result_list, start, end, chunk_length, sample_rate)