Functions — github.com/antgroup/echomimic

↓ 1 callersMethodprepare_latents

( self, batch_size, num_channels_latents, width, height, video

src/pipelines/pipeline_echo_mimic_acc.py:151

↓ 1 callersMethodprepare_latents

( self, batch_size, num_channels_latents, width, height, video

src/pipelines/pipeline_echo_mimic_pose_acc.py:181

↓ 1 callersFunctionprocess_video

(uploaded_img, uploaded_audio, width, height, length, seed, facemask_dilation_ratio, facecrop_dilation_ratio,

webgui.py:141

↓ 1 callersMethodprocess_words

(self, words: List[str])

src/models/whisper/whisper/normalizers/english.py:160

↓ 1 callersFunctionproject_points_with_trans

(points_3d, transformation_matrix, image_shape)

src/utils/motion_utils.py:66

↓ 1 callersMethodqkv_attention

(self, q: Tensor, k: Tensor, v: Tensor, mask: Optional[Tensor] = None)

src/models/whisper/whisper/model.py:88

↓ 1 callersMethodrank

Given a list of groups of samples and their cumulative log probabilities, return the indices of the samples in each group to select a

src/models/whisper/whisper/decoding.py:165

↓ 1 callersMethodrearrange_kv_cache

Update the key-value cache according to the updated beams

src/models/whisper/whisper/decoding.py:123

↓ 1 callersMethodregister_reference_hooks

( self, mode, do_classifier_free_guidance, attention_auto_machine_weight,

src/models/mutual_self_attention.py:52

↓ 1 callersFunctionremove_symbols_and_diacritics

Replace any other markers, symbols, and punctuations with a space, and drop any diacritics (category 'Mn' and some manual mappings)

src/models/whisper/whisper/normalizers/basic.py:27

↓ 1 callersMethodreset

Initialize any stateful variables for decoding a new sequence

src/models/whisper/whisper/decoding.py:200

↓ 1 callersFunctionsave_video_from_cv2_list

(pic_cv2_list, output_path, fps=30.0)

src/utils/img_utils.py:59

↓ 1 callersFunctionsave_videos_from_pil

(pil_images, path, fps=8, audio_path=None)

src/utils/util.py:51

↓ 1 callersFunctionselect_face

(det_bboxes, probs)

webgui.py:127

↓ 1 callersFunctionselect_face

(det_bboxes, probs)

infer_audio2vid_pose_acc.py:64

↓ 1 callersFunctionselect_face

(det_bboxes, probs)

infer_audio2vid_pose.py:58

↓ 1 callersFunctionselect_face

(det_bboxes, probs)

infer_audio2vid.py:74

↓ 1 callersFunctionselect_face

(det_bboxes, probs)

infer_audio2vid_acc.py:74

↓ 1 callersMethodset_attention_slice

r""" Enable sliced attention computation. When this option is enabled, the attention module will split the input tensor in slices, to

src/models/unet_3d.py:283

↓ 1 callersMethodset_attention_slice

r""" Enable sliced attention computation. When this option is enabled, the attention module splits the input tensor in slices to comp

src/models/unet_2d_condition.py:762

↓ 1 callersMethodset_attention_slice

r""" Enable sliced attention computation. When this option is enabled, the attention module will split the input tensor in slices, to

src/models/unet_3d_echo.py:291

↓ 1 callersMethodset_attn_processor

r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o

src/models/unet_2d_condition.py:701

↓ 1 callersFunctionsinusoids

Returns sinusoids for positional embedding

src/models/whisper/whisper/model.py:48

↓ 1 callersFunctiontranscribe

Transcribe an audio file using Whisper Parameters ---------- model: Whisper The Whisper model instance audio: Union[str

src/models/whisper/whisper/transcribe.py:19

↓ 1 callersFunctionwrite_srt

Write a transcript to a file in SRT format. Example usage: from pathlib import Path from whisper.utils import write_srt

src/models/whisper/whisper/utils.py:63

↓ 1 callersFunctionwrite_txt

(transcript: Iterator[dict], file: TextIO)

src/models/whisper/whisper/utils.py:47

↓ 1 callersFunctionwrite_vtt

(transcript: Iterator[dict], file: TextIO)

src/models/whisper/whisper/utils.py:52

Method__call__

(self, img)

src/utils/mp_utils.py:39

Method__call__

( self, ref_image, audio_path, face_mask_tensor, width, height

src/pipelines/pipeline_echo_mimic_pose.py:377

Method__call__

( self, ref_image, audio_path, face_mask_tensor, width, height

src/pipelines/pipeline_echo_mimic.py:338

Method__call__

( self, ref_image, audio_path, face_mask_tensor, width, height

src/pipelines/pipeline_echo_mimic_acc.py:339

Method__call__

( self, ref_image, audio_path, face_mask_tensor, width, height

src/pipelines/pipeline_echo_mimic_pose_acc.py:371

Method__call__

(self, s: str)

src/models/whisper/whisper/normalizers/english.py:435

Method__call__

(self, s: str)

src/models/whisper/whisper/normalizers/english.py:454

Method__call__

(self, s: str)

src/models/whisper/whisper/normalizers/english.py:519

Method__call__

(self, s: str)

src/models/whisper/whisper/normalizers/basic.py:60

Method__init__

(self, FPS=25)

src/utils/mp_utils.py:20

Method__init__

(self, forehead_edge=False, upface_only=False, draw_eye=True,

src/utils/draw_utils.py:7

Method__init__

( self, vae, reference_unet, denoising_unet, audio_guider, fac

src/pipelines/pipeline_echo_mimic_pose.py:38

Method__init__

( self, vae, reference_unet, denoising_unet, audio_guider, fac

src/pipelines/pipeline_echo_mimic.py:46

Method__init__

( self, vae, reference_unet, denoising_unet, audio_guider, fac

src/pipelines/pipeline_echo_mimic_acc.py:47

Method__init__

( self, vae, reference_unet, denoising_unet, audio_guider, fac

src/pipelines/pipeline_echo_mimic_pose_acc.py:39

Method__init__

( self, num_attention_heads: int = 16, attention_head_dim: int = 88, in_channe

src/models/transformer_3d.py:31

Method__init__

( self, unet, mode="write", do_classifier_free_guidance=False, attenti

src/models/mutual_self_attention.py:20

Method__init__

( self, num_attention_heads: int = 16, attention_head_dim: int = 88, in_channe

src/models/transformer_2d.py:63

Method__init__

( self, sample_size: Optional[int] = None, in_channels: int = 4, out_channels:

src/models/unet_3d.py:34

Method__init__

( self, sample_size: Optional[int] = None, in_channels: int = 4, out_channels:

src/models/unet_2d_condition.py:161

Method__init__

( self, dim: int, num_attention_heads: int, attention_head_dim: int, d

src/models/attention.py:245

Method__init__

( self, sample_size: Optional[int] = None, in_channels: int = 4, out_channels:

src/models/unet_3d_echo.py:42

Method__init__

(self, in_channels: int, out_channels: int, act_fn: str)

src/models/unet_2d_blocks.py:202

Method__init__

( self, in_channels: int, temb_channels: int, dropout: float = 0.0, nu

src/models/unet_2d_blocks.py:254

Method__init__

( self, in_channels: int, temb_channels: int, dropout: float = 0.0, nu

src/models/unet_2d_blocks.py:357

Method__init__

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

src/models/unet_2d_blocks.py:511

Method__init__

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

src/models/unet_2d_blocks.py:682

Method__init__

( self, in_channels: int, out_channels: int, prev_output_channel: int,

src/models/unet_2d_blocks.py:780

Method__init__

( self, in_channels: int, temb_channels: int, dropout: float = 0.0, nu

src/models/unet_3d_blocks.py:172

Method__init__

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

src/models/unet_3d_blocks.py:299

Method__init__

( self, in_channels: int, out_channels: int, temb_channels: int, dropo

src/models/unet_3d_blocks.py:473

Method__init__

( self, in_channels: int, out_channels: int, prev_output_channel: int,

src/models/unet_3d_blocks.py:592

Method__init__

( self, conditioning_embedding_channels: int, conditioning_channels: int = 1,

src/models/face_locator.py:13

Method__init__

( self, channels, use_conv=False, out_channels=None, padding=1, name="conv" )

src/models/resnet.py:94

Method__init__

( self, *, in_channels, out_channels=None, conv_shortcut=False,

src/models/resnet.py:124

Method__init__

( self, in_channels, num_attention_heads=8, num_transformer_block=2, a

src/models/motion_module.py:45

Method__init__

( self, in_channels, num_attention_heads, attention_head_dim, num_laye

src/models/motion_module.py:95

Method__init__

( self, dim, num_attention_heads, attention_head_dim, attention_block_

src/models/motion_module.py:186

Method__init__

( self, attention_mode=None, cross_frame_attention_mode=None, temporal_positio

src/models/motion_module.py:281

Method__init__

(self, whisper_model_type="tiny", model_path="./models/whisper/tiny.pt",

src/models/whisper/audio2feature.py:9

Method__init__

(self, model: "Whisper", initial_token_length: int)

src/models/whisper/whisper/decoding.py:133

Method__init__

(self, length_penalty: Optional[float])

src/models/whisper/whisper/decoding.py:179

Method__init__

(self, temperature: float, eot: int)

src/models/whisper/whisper/decoding.py:254

Method__init__

(self, beam_size: int, eot: int, inference: Inference, patience: Optional[float] = None)

src/models/whisper/whisper/decoding.py:282

Method__init__

(self, tokenizer: Tokenizer, sample_begin: int)

src/models/whisper/whisper/decoding.py:388

Method__init__

(self, suppress_tokens: Sequence[int])

src/models/whisper/whisper/decoding.py:398

Method__init__

( self, tokenizer: Tokenizer, sample_begin: int, max_initial_timestamp_index: Optional[int] )

src/models/whisper/whisper/decoding.py:406

Method__init__

(self, model: "Whisper", options: DecodingOptions)

src/models/whisper/whisper/decoding.py:450

Method__init__

(self, n_state: int, n_head: int)

src/models/whisper/whisper/model.py:58

Method__init__

(self, n_state: int, n_head: int, cross_attention: bool = False)

src/models/whisper/whisper/model.py:104

Method__init__

(self, n_mels: int, n_ctx: int, n_state: int, n_head: int, n_layer: int)

src/models/whisper/whisper/model.py:132

Method__init__

(self, n_vocab: int, n_ctx: int, n_state: int, n_head: int, n_layer: int)

src/models/whisper/whisper/model.py:175

Method__init__

(self)

src/models/whisper/whisper/normalizers/english.py:23

Method__init__

(self)

src/models/whisper/whisper/normalizers/english.py:450

Method__init__

(self, remove_diacritics: bool = False, split_letters: bool = False)

src/models/whisper/whisper/normalizers/basic.py:56

Method_conv_forward

(self, x: Tensor, weight: Tensor, bias: Optional[Tensor])

src/models/whisper/whisper/model.py:42

Method_encode_prompt

( self, prompt, device, num_videos_per_prompt, do_classifier_free_guid

src/pipelines/pipeline_echo_mimic_pose.py:223

Method_encode_prompt

( self, prompt, device, num_videos_per_prompt, do_classifier_free_guid

src/pipelines/pipeline_echo_mimic.py:184

Method_encode_prompt

( self, prompt, device, num_videos_per_prompt, do_classifier_free_guid

src/pipelines/pipeline_echo_mimic_acc.py:185

Method_encode_prompt

( self, prompt, device, num_videos_per_prompt, do_classifier_free_guid

src/pipelines/pipeline_echo_mimic_pose_acc.py:217

Method_execution_device

(self)

src/pipelines/pipeline_echo_mimic_pose.py:96

Method_execution_device

(self)

src/pipelines/pipeline_echo_mimic.py:103

Method_execution_device

(self)

src/pipelines/pipeline_echo_mimic_acc.py:104

Method_execution_device

(self)

src/pipelines/pipeline_echo_mimic_pose_acc.py:97