Index

A

add_decomposed_rel_pos() (in module pretrained.sam) apply_boxes() (pretrained.sam.ResizeLongestSide method) apply_boxes_torch() (pretrained.sam.ResizeLongestSide method) apply_coords() (pretrained.sam.ResizeLongestSide method) apply_coords_torch() (pretrained.sam.ResizeLongestSide method) apply_image() (pretrained.sam.ResizeLongestSide method) apply_image_torch() (pretrained.sam.ResizeLongestSide method) apply_rotary_emb() (in module pretrained.llama) Attention (class in pretrained.blip) (class in pretrained.causal_hubert) (class in pretrained.hubert) (class in pretrained.llama) (class in pretrained.rwkv) (class in pretrained.sam) (class in pretrained.tacotron2)

attention() (pretrained.clip.ResidualAttentionBlock method) attention_dim (pretrained.tacotron2.DecoderConfig attribute) attention_location_kernel_size (pretrained.tacotron2.DecoderConfig attribute) attention_location_n_filters (pretrained.tacotron2.DecoderConfig attribute) attention_rnn_dim (pretrained.tacotron2.DecoderConfig attribute) AttentionPool2d (class in pretrained.clip) attn_c (pretrained.tacotron2.DecoderStates attribute) attn_ctx (pretrained.tacotron2.DecoderStates attribute) attn_drop_rate (pretrained.blip.ViTParams attribute) attn_h (pretrained.tacotron2.DecoderStates attribute) attn_states (pretrained.causal_hubert.CausalHubertState attribute) attn_weights (pretrained.tacotron2.DecoderStates attribute) attn_weights_cum (pretrained.tacotron2.DecoderStates attribute) audio_to_mels() (pretrained.vocoder.hifigan.HiFiGAN method) AudioToHifiGanMels (class in pretrained.vocoder.hifigan)

B

backward() (pretrained.rwkv.WkvLogSpace static method) (pretrained.rwkv.WkvWithEps static method) Blip (class in pretrained.blip) BlipPredictor (class in pretrained.blip) Block (class in pretrained.blip) (class in pretrained.rwkv) (class in pretrained.sam)

Bottleneck (class in pretrained.clip) bpe() (pretrained.clip.ClipTokenizer method) build_attention_mask() (pretrained.clip.Clip method) (pretrained.clip.TextModel method) bytes_to_unicode() (in module pretrained.clip)

C

cast_pretrained_blip_key() (in module pretrained.blip) cast_pretrained_causal_hubert_key() (in module pretrained.causal_hubert) cast_pretrained_clip_key() (in module pretrained.clip) cast_pretrained_encodec_type() (in module pretrained.encodec) cast_pretrained_hifigan_type() (in module pretrained.vocoder.hifigan) cast_pretrained_hubert_kmeans_size() (in module pretrained.hubert) cast_pretrained_hubert_size() (in module pretrained.hubert) cast_pretrained_llama_key() (in module pretrained.llama) cast_pretrained_mel_codec_type() (in module pretrained.mel_codec) (in module pretrained.wav_codec) cast_pretrained_rwkv_key() (in module pretrained.rwkv) cast_pretrained_sam_size() (in module pretrained.sam)

causal (pretrained.encodec.EncodecConfig attribute) CausalHubert (class in pretrained.causal_hubert) CausalHubertPredictor (class in pretrained.causal_hubert) CausalHubertState (class in pretrained.causal_hubert) CBR (class in pretrained.mel_codec) (class in pretrained.wav_codec) channels (pretrained.encodec.EncodecConfig attribute) Clip (class in pretrained.clip) ClipPredictor (class in pretrained.clip) ClipTokenizer (class in pretrained.clip) convert_weights() (in module pretrained.clip) ConvExtractor (class in pretrained.causal_hubert) ConvNorm (class in pretrained.tacotron2)

D

dec_c (pretrained.tacotron2.DecoderStates attribute) dec_h (pretrained.tacotron2.DecoderStates attribute) decode() (pretrained.clip.ClipTokenizer method) (pretrained.encodec.Decoder method) (pretrained.encodec.Encodec method) (pretrained.llama.Tokenizer method) (pretrained.mel_codec.MelCodecDequantizer method) (pretrained.tacotron2.Decoder method) (pretrained.wav_codec.WavCodec method) (pretrained.wav_codec.WavCodecDequantizer method) Decoder (class in pretrained.demucs) (class in pretrained.encodec) (class in pretrained.mel_codec) (class in pretrained.tacotron2) (class in pretrained.wav_codec)

decoder (pretrained.tacotron2.TacotronConfig attribute) decoder_rnn_dim (pretrained.tacotron2.DecoderConfig attribute) DecoderConfig (class in pretrained.tacotron2) DecoderStates (class in pretrained.tacotron2) default_bpe() (in module pretrained.clip) Demucs (class in pretrained.demucs) DemucsStreamer (class in pretrained.demucs) depth (pretrained.blip.ViTParams attribute) dequantizer() (pretrained.mel_codec.MelCodec method) (pretrained.wav_codec.WavCodec method) device (pretrained.sam.Sam property) dim (pretrained.llama.ModelArgs attribute) downsample2() (in module pretrained.demucs) drop_rate (pretrained.blip.ViTParams attribute) dynamic_range_compression() (in module pretrained.tacotron2) dynamic_range_decompression() (in module pretrained.tacotron2)

E

emb_dim (pretrained.rwkv.ModelArgs attribute) (pretrained.tacotron2.EncoderConfig attribute) (pretrained.tacotron2.PostnetConfig attribute) embed_dim (pretrained.blip.ViTParams attribute) empty_llama() (in module pretrained.llama) encode() (pretrained.clip.ClipTokenizer method) (pretrained.encodec.Encodec method) (pretrained.encodec.Encoder method) (pretrained.llama.Tokenizer method) (pretrained.mel_codec.MelCodecQuantizer method) (pretrained.wav_codec.WavCodec method) (pretrained.wav_codec.WavCodecQuantizer method) encode_image() (pretrained.clip.Clip method) encode_text() (pretrained.clip.Clip method) Encodec (class in pretrained.encodec) EncodecConfig (class in pretrained.encodec)

Encoder (class in pretrained.demucs) (class in pretrained.encodec) (class in pretrained.mel_codec) (class in pretrained.tacotron2) (class in pretrained.wav_codec) encoder (pretrained.tacotron2.TacotronConfig attribute) encoder_depth (pretrained.sam.PretrainedModelConfig attribute) encoder_emb_dim (pretrained.tacotron2.DecoderConfig attribute) encoder_embed_dim (pretrained.sam.PretrainedModelConfig attribute) encoder_global_attn_indices (pretrained.sam.PretrainedModelConfig attribute) encoder_num_heads (pretrained.sam.PretrainedModelConfig attribute) EncoderConfig (class in pretrained.tacotron2) ensure_tacotron_downloaded() (in module pretrained.tacotron2) expansion (pretrained.clip.Bottleneck attribute) extract_all_features() (pretrained.hubert.Hubert method) (pretrained.hubert.HubertEncoder method) (pretrained.hubert.HubertEncoderStableLayerNorm method)

F

fast_conv() (in module pretrained.demucs) feed() (pretrained.demucs.DemucsStreamer method) FeedForward (class in pretrained.causal_hubert) (class in pretrained.hubert) (class in pretrained.llama) (class in pretrained.rwkv) flush() (pretrained.demucs.DemucsStreamer method) forward() (pretrained.blip.Attention method) (pretrained.blip.Blip method) (pretrained.blip.Block method) (pretrained.blip.Mlp method) (pretrained.blip.PatchEmbed method) (pretrained.blip.VisionTransformer method) (pretrained.causal_hubert.Attention method) (pretrained.causal_hubert.CausalHubert method) (pretrained.causal_hubert.CausalHubertPredictor method) (pretrained.causal_hubert.ConvExtractor method) (pretrained.causal_hubert.FeedForward method) (pretrained.causal_hubert.LinearExtractor method) (pretrained.causal_hubert.SelfAttention method) (pretrained.causal_hubert.SelfAttentionLayer method) (pretrained.clip.AttentionPool2d method) (pretrained.clip.Bottleneck method) (pretrained.clip.Clip method) (pretrained.clip.ModifiedResNet method) (pretrained.clip.QuickGELU method) (pretrained.clip.ResidualAttentionBlock method) (pretrained.clip.TextModel method) (pretrained.clip.Transformer method) (pretrained.clip.VisionTransformer method) (pretrained.demucs.Decoder method) (pretrained.demucs.Demucs method) (pretrained.demucs.Encoder method) (pretrained.demucs.RNN method) (pretrained.encodec.Decoder method) (pretrained.encodec.Encodec method) (pretrained.encodec.Encoder method) (pretrained.encodec.NormConv1d method) (pretrained.encodec.NormConvTranspose1d method) (pretrained.encodec.SConv1d method) (pretrained.encodec.SConvTranspose1d method) (pretrained.encodec.SEANetDecoder method) (pretrained.encodec.SEANetEncoder method) (pretrained.encodec.SEANetResnetBlock method) (pretrained.encodec.SLSTM method) (pretrained.hubert.Attention method) (pretrained.hubert.FeedForward method) (pretrained.hubert.GroupNormConvLayer method) (pretrained.hubert.Hubert method) (pretrained.hubert.HubertEncoder method) (pretrained.hubert.HubertEncoderLayer method) (pretrained.hubert.HubertEncoderLayerStableLayerNorm method) (pretrained.hubert.HubertEncoderStableLayerNorm method) (pretrained.hubert.HubertFeatureEncoder method) (pretrained.hubert.HubertFeatureProjection method) (pretrained.hubert.HubertSamePadLayer method) (pretrained.hubert.LayerNormConvLayer method) (pretrained.hubert.NoLayerNormConvLayer method) (pretrained.hubert.PositionalConvEmbedding method) (pretrained.llama.Attention method) (pretrained.llama.FeedForward method) (pretrained.llama.Llama method) (pretrained.llama.RMSNorm method) (pretrained.llama.TransformerBlock method) (pretrained.mel_codec.CBR method) (pretrained.mel_codec.Decoder method) (pretrained.mel_codec.Encoder method) (pretrained.mel_codec.MelCodec method) (pretrained.mel_codec.MelCodecDequantizer method) (pretrained.mel_codec.MelCodecQuantizer method) (pretrained.rwkv.Attention method) (pretrained.rwkv.Block method) (pretrained.rwkv.FeedForward method) (pretrained.rwkv.Rwkv method) (pretrained.rwkv.RwkvStack method) (pretrained.rwkv.WkvLogSpace static method) (pretrained.rwkv.WkvWithEps static method) (pretrained.sam.Attention method) (pretrained.sam.Block method) (pretrained.sam.ImageEncoderViT method) (pretrained.sam.LayerNorm2d method) (pretrained.sam.MaskDecoder method) (pretrained.sam.MLP method) (pretrained.sam.MLPBlock method) (pretrained.sam.PatchEmbed method) (pretrained.sam.PositionEmbeddingRandom method) (pretrained.sam.PromptEncoder method) (pretrained.sam.Sam method) (pretrained.sam.TwoWayAttentionBlock method) (pretrained.sam.TwoWayAttentionFunction method) (pretrained.sam.TwoWayTransformer method) (pretrained.tacotron2.Attention method) (pretrained.tacotron2.ConvNorm method) (pretrained.tacotron2.Decoder method) (pretrained.tacotron2.Encoder method) (pretrained.tacotron2.LinearNorm method) (pretrained.tacotron2.LocationLayer method) (pretrained.tacotron2.Postnet method) (pretrained.tacotron2.Prenet method) (pretrained.tacotron2.STFT method) (pretrained.tacotron2.Tacotron method) (pretrained.vocoder.hifigan.AudioToHifiGanMels method) (pretrained.vocoder.hifigan.HiFiGAN method) (pretrained.vocoder.hifigan.ResBlock method) (pretrained.vocoder.waveglow.Invertible1x1Conv method) (pretrained.vocoder.waveglow.WaveGlow method) (pretrained.vocoder.waveglow.WaveGlowLoss method) (pretrained.vocoder.waveglow.WaveNet method) (pretrained.wav_codec.CBR method) (pretrained.wav_codec.Decoder method) (pretrained.wav_codec.Encoder method) (pretrained.wav_codec.WavCodec method) (pretrained.wav_codec.WavCodecDequantizer method) (pretrained.wav_codec.WavCodecQuantizer method)

forward_basis (pretrained.tacotron2.STFT attribute) forward_with_coords() (pretrained.sam.PositionEmbeddingRandom method) freeze_bn (pretrained.tacotron2.EncoderConfig attribute) freqs_cis (pretrained.llama.Llama attribute)

G

gate_threshold (pretrained.tacotron2.DecoderConfig attribute) generate() (pretrained.llama.LlamaPredictor method) (pretrained.rwkv.RwkvPredictor method) (pretrained.tacotron2.TTS method) generate_for_tokens() (pretrained.llama.LlamaPredictor method) generate_mels() (pretrained.tacotron2.TTS method) generate_wave() (pretrained.tacotron2.TTS method) get() (in module pretrained.vocoder.hifigan) get_alignment_energies() (pretrained.tacotron2.Attention method) get_ckpt_and_tokenizer_path() (in module pretrained.llama) get_decoder() (pretrained.encodec.Encodec method) get_default_wkv_fn_key() (in module pretrained.rwkv) get_dense_pe() (pretrained.sam.PromptEncoder method) get_encoder() (pretrained.encodec.Encodec method) get_extra_padding_for_conv1d() (in module pretrained.encodec) get_go_frame() (pretrained.tacotron2.Decoder method)

get_image_embedding() (pretrained.sam.SamPredictor method) get_input_image() (pretrained.blip.BlipPredictor method) get_mask() (pretrained.llama.Llama method) get_mask_from_lengths() (in module pretrained.tacotron2) get_pairs() (in module pretrained.clip) get_pil_preprocess() (pretrained.clip.Clip method) get_preprocess_shape() (pretrained.sam.ResizeLongestSide static method) get_pretrained_path() (in module pretrained.clip) (in module pretrained.sam) get_rel_pos() (in module pretrained.sam) get_tensor_preprocess() (pretrained.clip.Clip method) get_tokenizer() (in module pretrained.rwkv) (pretrained.clip.TextModel method) get_wkv_fn() (in module pretrained.rwkv) get_wkv_fn_cuda() (in module pretrained.rwkv) griffin_lim() (in module pretrained.tacotron2) GroupNormConvLayer (class in pretrained.hubert)

H

hann_window (pretrained.vocoder.hifigan.AudioToHifiGanMels attribute) HiFiGAN (class in pretrained.vocoder.hifigan) hifigan (pretrained.mel_codec.MelCodec property) Hubert (class in pretrained.hubert) HubertEncoder (class in pretrained.hubert) HubertEncoderLayer (class in pretrained.hubert)

HubertEncoderLayerStableLayerNorm (class in pretrained.hubert) HubertEncoderStableLayerNorm (class in pretrained.hubert) HubertFeatureEncoder (class in pretrained.hubert) HubertFeatureProjection (class in pretrained.hubert) HubertPredictor (class in pretrained.hubert) HubertSamePadLayer (class in pretrained.hubert)

I

image_format (pretrained.sam.Sam attribute) ImageEncoderViT (class in pretrained.sam) img_size (pretrained.blip.ViTParams attribute) in_chans (pretrained.blip.ViTParams attribute) infer() (pretrained.llama.Llama method) (pretrained.mel_codec.Decoder method) (pretrained.mel_codec.MelCodec method) (pretrained.tacotron2.Decoder method) (pretrained.tacotron2.Encoder method) (pretrained.tacotron2.Tacotron method) (pretrained.vocoder.hifigan.HiFiGAN method) (pretrained.vocoder.waveglow.Invertible1x1Conv method) (pretrained.vocoder.waveglow.WaveGlow method) (pretrained.wav_codec.Decoder method)

init_emb (pretrained.mel_codec.Decoder attribute) init_hifigan_weights() (in module pretrained.vocoder.hifigan) init_state (pretrained.rwkv.Attention attribute) (pretrained.rwkv.FeedForward attribute) init_x (pretrained.rwkv.Attention attribute) initial_state_log_space() (in module pretrained.rwkv) initial_state_with_eps() (in module pretrained.rwkv) initialize_decoder_states() (pretrained.tacotron2.Decoder method) initialize_parameters() (pretrained.clip.Clip method) (pretrained.clip.ModifiedResNet method) (pretrained.clip.TextModel method) inverse() (pretrained.tacotron2.STFT method) inverse_basis (pretrained.tacotron2.STFT attribute) Invertible1x1Conv (class in pretrained.vocoder.waveglow)

K

kernel_downsample2() (in module pretrained.demucs) kernel_size (pretrained.tacotron2.EncoderConfig attribute) (pretrained.tacotron2.PostnetConfig attribute) (pretrained.vocoder.waveglow.WaveNetConfig attribute)

kernel_upsample2() (in module pretrained.demucs) key (pretrained.causal_hubert.SelfAttentionState attribute)

L

LayerNorm2d (class in pretrained.sam) LayerNormConvLayer (class in pretrained.hubert) LayerNormHigherEps (class in pretrained.sam) LinearExtractor (class in pretrained.causal_hubert) LinearNorm (class in pretrained.tacotron2) Llama (class in pretrained.llama) LlamaPredictor (class in pretrained.llama) LocationLayer (class in pretrained.tacotron2) lora_alpha (pretrained.tacotron2.DecoderConfig attribute) (pretrained.tacotron2.EncoderConfig attribute) (pretrained.tacotron2.PostnetConfig attribute)

lora_dropout (pretrained.tacotron2.DecoderConfig attribute) (pretrained.tacotron2.EncoderConfig attribute) (pretrained.tacotron2.PostnetConfig attribute) lora_rank (pretrained.tacotron2.DecoderConfig attribute) (pretrained.tacotron2.EncoderConfig attribute) (pretrained.tacotron2.PostnetConfig attribute) (pretrained.vocoder.waveglow.WaveGlowConfig attribute)

M

mask (pretrained.causal_hubert.SelfAttention attribute) (pretrained.tacotron2.DecoderStates attribute) mask_padding (pretrained.tacotron2.TacotronConfig attribute) mask_threshold (pretrained.sam.Sam attribute) MaskDecoder (class in pretrained.sam) max_decoder_steps (pretrained.tacotron2.DecoderConfig attribute) max_seq_len (pretrained.llama.ModelArgs attribute) mel_basis (pretrained.tacotron2.TacotronSTFT attribute) (pretrained.vocoder.hifigan.AudioToHifiGanMels attribute) mel_spectrogram() (pretrained.tacotron2.TacotronSTFT method) MelCodec (class in pretrained.mel_codec) MelCodecDequantizer (class in pretrained.mel_codec) MelCodecQuantizer (class in pretrained.mel_codec) memory (pretrained.tacotron2.DecoderStates attribute) Mlp (class in pretrained.blip) MLP (class in pretrained.sam) mlp_ratio (pretrained.blip.ViTParams attribute) MLPBlock (class in pretrained.sam) ModelArgs (class in pretrained.llama) (class in pretrained.rwkv)

ModelParams (class in pretrained.blip) ModifiedResNet (class in pretrained.clip) module pretrained.blip pretrained.causal_hubert pretrained.clip pretrained.demucs pretrained.encodec pretrained.hubert pretrained.llama pretrained.mel_codec pretrained.rwkv pretrained.sam pretrained.tacotron2 pretrained.vocoder.hifigan pretrained.vocoder.waveglow pretrained.wav_codec mp_size (pretrained.llama.ModelArgs attribute) multiple_of (pretrained.llama.ModelArgs attribute)

N

n_channels (pretrained.vocoder.waveglow.WaveNetConfig attribute) n_convolutions (pretrained.tacotron2.EncoderConfig attribute) (pretrained.tacotron2.PostnetConfig attribute) n_early_every (pretrained.vocoder.waveglow.WaveGlowConfig attribute) n_early_size (pretrained.vocoder.waveglow.WaveGlowConfig attribute) n_flows (pretrained.vocoder.waveglow.WaveGlowConfig attribute) n_frames_per_step (pretrained.tacotron2.DecoderConfig attribute) (pretrained.tacotron2.TacotronConfig attribute) n_group (pretrained.vocoder.waveglow.WaveGlowConfig attribute) n_heads (pretrained.llama.ModelArgs attribute) n_layers (pretrained.llama.ModelArgs attribute) (pretrained.vocoder.waveglow.WaveNetConfig attribute) n_mel_channels (pretrained.tacotron2.DecoderConfig attribute) (pretrained.tacotron2.PostnetConfig attribute) (pretrained.tacotron2.TacotronConfig attribute) (pretrained.vocoder.waveglow.WaveGlowConfig attribute)

n_symbols (pretrained.tacotron2.TacotronConfig attribute) NoLayerNormConvLayer (class in pretrained.hubert) norm (pretrained.encodec.EncodecConfig attribute) norm_eps (pretrained.llama.ModelArgs attribute) norm_type (pretrained.blip.ViTParams attribute) normalize_output_layer() (in module pretrained.hubert) Normalizer (class in pretrained.tacotron2) NormConv1d (class in pretrained.encodec) NormConvTranspose1d (class in pretrained.encodec) num_heads (pretrained.blip.ViTParams attribute) num_layers (pretrained.rwkv.ModelArgs attribute) num_quantizers (pretrained.encodec.EncodecConfig attribute) num_tokens (pretrained.blip.TextParams attribute)

O

offset (pretrained.causal_hubert.CausalHubertState attribute)

P

p_attention_dropout (pretrained.tacotron2.DecoderConfig attribute) p_decoder_dropout (pretrained.tacotron2.DecoderConfig attribute) pad1d() (in module pretrained.encodec) parse_decoder_inputs() (pretrained.tacotron2.Decoder method) parse_decoder_outputs() (pretrained.tacotron2.Decoder method) parse_output() (pretrained.tacotron2.Tacotron method) patch_size (pretrained.blip.ViTParams attribute) PatchEmbed (class in pretrained.blip) (class in pretrained.sam) pil_preprocess() (in module pretrained.clip) pixel_mean (pretrained.sam.Sam attribute) pixel_std (pretrained.sam.Sam attribute) positional_encoding_gaussian_matrix (pretrained.sam.PositionEmbeddingRandom attribute) PositionalConvEmbedding (class in pretrained.hubert) PositionEmbeddingRandom (class in pretrained.sam) Postnet (class in pretrained.tacotron2) postnet (pretrained.tacotron2.TacotronConfig attribute) PostnetConfig (class in pretrained.tacotron2) postprocess_masks() (pretrained.sam.Sam method) precompute_freqs_cis() (in module pretrained.llama) predict() (pretrained.blip.BlipPredictor method) (pretrained.hubert.HubertPredictor method) (pretrained.sam.SamPredictor method) predict_file() (pretrained.hubert.HubertPredictor method) predict_image() (pretrained.clip.ClipPredictor method) predict_in_chunks() (pretrained.hubert.HubertPredictor method) predict_masks() (pretrained.sam.MaskDecoder method) predict_text() (pretrained.clip.ClipPredictor method) predict_torch() (pretrained.sam.SamPredictor method) predictor() (pretrained.blip.Blip method) (pretrained.causal_hubert.CausalHubert method) (pretrained.clip.Clip method) (pretrained.hubert.Hubert method) (pretrained.llama.Llama method) (pretrained.rwkv.Rwkv method) (pretrained.sam.Sam method) Prenet (class in pretrained.tacotron2) prenet_dim (pretrained.tacotron2.DecoderConfig attribute) prenet_dropout (pretrained.tacotron2.DecoderConfig attribute) prenet_dropout_always_on (pretrained.tacotron2.DecoderConfig attribute) preprocess() (pretrained.sam.Sam method) pretrained.blip module pretrained.causal_hubert module

pretrained.clip module pretrained.demucs module pretrained.encodec module pretrained.hubert module pretrained.llama module pretrained.mel_codec module pretrained.rwkv module pretrained.sam module pretrained.tacotron2 module pretrained.vocoder.hifigan module pretrained.vocoder.waveglow module pretrained.wav_codec module pretrained_blip() (in module pretrained.blip) pretrained_causal_hubert() (in module pretrained.causal_hubert) pretrained_clip() (in module pretrained.clip) pretrained_encodec() (in module pretrained.encodec) pretrained_hifigan() (in module pretrained.vocoder.hifigan) pretrained_hubert() (in module pretrained.hubert) pretrained_hubert_with_kmeans() (in module pretrained.hubert) pretrained_kmeans_clusters() (in module pretrained.hubert) pretrained_llama() (in module pretrained.llama) pretrained_mel_codec() (in module pretrained.mel_codec) pretrained_rwkv() (in module pretrained.rwkv) pretrained_sam() (in module pretrained.sam) pretrained_tacotron2() (in module pretrained.tacotron2) pretrained_tacotron2_tts() (in module pretrained.tacotron2) pretrained_wav_codec() (in module pretrained.wav_codec) pretrained_waveglow() (in module pretrained.vocoder.waveglow) PretrainedModelConfig (class in pretrained.sam) processed_memory (pretrained.tacotron2.DecoderStates attribute) PromptEncoder (class in pretrained.sam)

Q

qkv_bias (pretrained.blip.ViTParams attribute) quantizer() (pretrained.mel_codec.MelCodec method) (pretrained.wav_codec.WavCodec method)

QuickGELU (class in pretrained.clip)

R

remove_weight_norm() (pretrained.vocoder.hifigan.HiFiGAN method) (pretrained.vocoder.hifigan.ResBlock method) (pretrained.vocoder.waveglow.WaveGlow method) ResBlock (class in pretrained.vocoder.hifigan) rescale_conv() (in module pretrained.demucs) rescale_module() (in module pretrained.demucs) reset_image() (pretrained.sam.SamPredictor method) reset_parameters() (pretrained.llama.RMSNorm method) reset_time_per_frame() (pretrained.demucs.DemucsStreamer method) reshape_for_broadcast() (in module pretrained.llama)

ResidualAttentionBlock (class in pretrained.clip) ResizeLongestSide (class in pretrained.sam) RMSNorm (class in pretrained.llama) RNN (class in pretrained.demucs) run_attn() (pretrained.llama.TransformerBlock method) (pretrained.rwkv.Block method) run_ffn() (pretrained.llama.TransformerBlock method) (pretrained.rwkv.Block method) Rwkv (class in pretrained.rwkv) RwkvPredictor (class in pretrained.rwkv) RwkvStack (class in pretrained.rwkv)

S

Sam (class in pretrained.sam) sample_probs() (pretrained.rwkv.RwkvPredictor method) sample_rate (pretrained.encodec.EncodecConfig attribute) sample_top_p() (in module pretrained.llama) sampling_rate (pretrained.vocoder.waveglow.WaveGlowConfig attribute) SamPredictor (class in pretrained.sam) SConv1d (class in pretrained.encodec) SConvTranspose1d (class in pretrained.encodec) SEANetDecoder (class in pretrained.encodec) SEANetEncoder (class in pretrained.encodec) SEANetResnetBlock (class in pretrained.encodec) SelfAttention (class in pretrained.causal_hubert) SelfAttentionLayer (class in pretrained.causal_hubert) SelfAttentionState (class in pretrained.causal_hubert) set_image() (pretrained.sam.SamPredictor method)

set_output_layer() (pretrained.hubert.Hubert method) set_torch_image() (pretrained.sam.SamPredictor method) setup() (in module pretrained.llama) sha256 (pretrained.rwkv.ModelArgs attribute) sinc() (in module pretrained.demucs) SLSTM (class in pretrained.encodec) speaker_emb_dim (pretrained.tacotron2.EncoderConfig attribute) spectral_de_normalize() (pretrained.tacotron2.TacotronSTFT method) spectral_normalize() (pretrained.tacotron2.TacotronSTFT method) split_waveform() (in module pretrained.wav_codec) stem() (pretrained.clip.ModifiedResNet method) STFT (class in pretrained.tacotron2) streamer() (pretrained.demucs.Demucs method) supports_triton() (in module pretrained.rwkv) symbols_emb_dim (pretrained.tacotron2.TacotronConfig attribute) symbols_emb_dropout (pretrained.tacotron2.TacotronConfig attribute)

T

Tacotron (class in pretrained.tacotron2) tacotron_stft() (in module pretrained.tacotron2) tacotron_tokenizer() (in module pretrained.tacotron2) TacotronConfig (class in pretrained.tacotron2) TacotronSTFT (class in pretrained.tacotron2) tensor_preprocess() (in module pretrained.clip) tensor_to() (pretrained.rwkv.Rwkv method) test_blip_adhoc() (in module pretrained.blip) test_causal_hubert() (in module pretrained.causal_hubert) test_codec_adhoc() (in module pretrained.mel_codec) (in module pretrained.wav_codec) test_codec_training_adhoc() (in module pretrained.wav_codec) test_encodec_adhoc() (in module pretrained.encodec) test_hubert_adhoc() (in module pretrained.hubert) test_mel_to_audio_adhoc() (in module pretrained.vocoder.hifigan) test_pretrained_model() (in module pretrained.clip) (in module pretrained.llama) (in module pretrained.sam) test_rwkv_adhoc() (in module pretrained.rwkv) test_tacotron_adhoc() (in module pretrained.tacotron2)

test_worker() (in module pretrained.llama) text_clean_func() (in module pretrained.clip) (in module pretrained.tacotron2) TextModel (class in pretrained.clip) TextParams (class in pretrained.blip) time_per_frame (pretrained.demucs.DemucsStreamer property) time_shift() (pretrained.rwkv.Attention method) (pretrained.rwkv.FeedForward method) tokenize() (pretrained.clip.ClipTokenizer method) (pretrained.llama.LlamaPredictor method) Tokenizer (class in pretrained.llama) (class in pretrained.tacotron2) total_stride (pretrained.demucs.Demucs property) transform() (pretrained.tacotron2.STFT method) Transformer (class in pretrained.clip) TransformerBlock (class in pretrained.llama) TTS (class in pretrained.tacotron2) TwoWayAttentionBlock (class in pretrained.sam) TwoWayAttentionFunction (class in pretrained.sam) TwoWayTransformer (class in pretrained.sam)

U

unit_test_forward_matches_infer() (pretrained.llama.LlamaPredictor method) unpad1d() (in module pretrained.encodec) upsample2() (in module pretrained.demucs)

url (pretrained.blip.ModelParams attribute) (pretrained.rwkv.ModelArgs attribute) (pretrained.sam.PretrainedModelConfig attribute) use_checkpointing (pretrained.llama.ModelArgs attribute)

V

valid_length() (pretrained.demucs.Demucs method) value (pretrained.causal_hubert.SelfAttentionState attribute) VisionTransformer (class in pretrained.blip) (class in pretrained.clip)

vit (pretrained.blip.ModelParams attribute) ViTParams (class in pretrained.blip) vocab_size (pretrained.llama.ModelArgs attribute)

W

wav_to_mels() (pretrained.vocoder.hifigan.AudioToHifiGanMels method) WavCodec (class in pretrained.wav_codec) WavCodecDequantizer (class in pretrained.wav_codec) WavCodecQuantizer (class in pretrained.wav_codec) waveform_leftover (pretrained.causal_hubert.CausalHubertState attribute) WaveGlow (class in pretrained.vocoder.waveglow) WaveGlowConfig (class in pretrained.vocoder.waveglow) WaveGlowLoss (class in pretrained.vocoder.waveglow) WaveNet (class in pretrained.vocoder.waveglow)

wavenet (pretrained.vocoder.waveglow.WaveGlowConfig attribute) WaveNetConfig (class in pretrained.vocoder.waveglow) weight_inv (pretrained.vocoder.waveglow.Invertible1x1Conv attribute) window_partition() (in module pretrained.sam) window_sumsquare() (in module pretrained.tacotron2) window_unpartition() (in module pretrained.sam) wkv_log_space() (in module pretrained.rwkv) wkv_with_eps() (in module pretrained.rwkv) WkvLogSpace (class in pretrained.rwkv) WkvWithEps (class in pretrained.rwkv)