Functions — github.com/AIFSH/NativeSpeaker

hub / github.com/AIFSH/NativeSpeaker / functions

Functions601 in github.com/AIFSH/NativeSpeaker

⨍ Functions 601◇ Types & classes 161

↓ 42 callersMethodinfo

(self, message)

src/log_helper.py:140

↓ 15 callersFunctionload_file_from_url

Ref:https://github.com/1adrianb/face-alignment/blob/master/face_alignment/utils.py

src/third_part/facelib/utils/misc.py:86

↓ 13 callersFunctionconv_dw

(inp, oup, stride, leaky=0.1)

src/third_part/facelib/detection/retinaface/retinaface_net.py:25

↓ 10 callersMethod__init__

(self, c1, c2, n=1, shortcut=True, g=1, e=0.5)

src/third_part/facelib/detection/yolov5face/models/common.py:108

↓ 10 callersMethodsplit

(self, music_file)

src/audio_bgm_split.py:48

↓ 9 callersMethod__init__

(self, in_channels, nf, emb_dim, ch_mult, num_res_blocks, resolution, attn_resolutions)

src/third_part/codeformer/vqgan_arch.py:230

↓ 9 callersMethodcreate_temp_file

(self, suffix)

src/temp_manager.py:15

↓ 8 callersMethodstack

(items)

src/third_part/whisperx/asr.py:166

↓ 7 callersMethodcritical

(self, message)

src/log_helper.py:149

↓ 7 callersFunctionload_audio

Open an audio file and read as mono waveform, resampling as necessary Parameters ---------- file: str The audio file to open

src/third_part/whisperx/audio.py:25

↓ 7 callersFunctionnormalize

(in_channels)

src/third_part/codeformer/vqgan_arch.py:14

↓ 7 callersMethodtolist

(self)

src/third_part/facelib/detection/yolov5face/models/common.py:293

↓ 6 callersMethodencode

(self, features: np.ndarray)

src/third_part/whisperx/asr.py:77

↓ 6 callersMethodformat_timestamp

(self, seconds: float)

src/third_part/whisperx/utils.py:325

↓ 5 callersMethod__console

构造日志收集器

src/log_helper.py:105

↓ 5 callersMethod__init__

(self, in_channel, out_channel)

src/third_part/facelib/detection/retinaface/retinaface_net.py:38

↓ 5 callersMethod__init__

(self, num_class)

src/third_part/facelib/parsing/bisenet.py:112

↓ 5 callersFunctioncmb_spectrogram_to_wave

(spec_m, mp, extra_bins_h=None, extra_bins=None)

src/third_part/uvr5_pack/lib_v5/spec_utils.py:349

↓ 5 callersFunctionconv_bn

(inp, oup, stride=1, leaky=0)

src/third_part/facelib/detection/retinaface/retinaface_net.py:6

↓ 5 callersFunctionimwrite

Write image to file. Args: img (ndarray): Image array to be written. file_path (str): Image file path. params (None or li

src/third_part/facelib/utils/misc.py:38

↓ 5 callersMethodsave

(self, filename="subtitles.srt", advanced_splitting=True)

src/third_part/whisperx/SubtitlesProcessor.py:206

↓ 5 callersFunctiontformfwd

Function: ---------- apply affine transform 'trans' to uv Parameters: ---------- @trans: 3x3 np.array tr

src/third_part/facelib/detection/matlab_cp2tform.py:13

↓ 5 callersMethodwarning

(self, message)

src/log_helper.py:143

↓ 4 callersMethod__init__

(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)

src/third_part/uvr5_pack/lib_v5/layers_123812KB .py:53

↓ 4 callersMethod__init__

(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)

src/third_part/uvr5_pack/lib_v5/layers_33966KB.py:53

↓ 4 callersMethod__init__

(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)

src/third_part/uvr5_pack/lib_v5/layers.py:53

↓ 4 callersMethod__init__

(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)

src/third_part/uvr5_pack/lib_v5/layers_537227KB.py:53

↓ 4 callersMethod__init__

(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)

src/third_part/uvr5_pack/lib_v5/layers_123821KB.py:53

↓ 4 callersMethod__init__

(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)

src/third_part/uvr5_pack/lib_v5/layers_new.py:30

↓ 4 callersMethod__init__

(self, nin, nout, ksize=3, stride=1, pad=1, activ=nn.LeakyReLU)

src/third_part/uvr5_pack/lib_v5/layers_537238KB.py:53

↓ 4 callersMethod__init__

(self, in_size=128, out_size=128, min_feat_size=32,

src/third_part/facelib/parsing/parsenet.py:142

↓ 4 callersMethod__init__

(self, num_modules=1)

src/third_part/wav2lip/face_detection/models.py:147

↓ 4 callersMethod_make_layer

(self, block, planes, blocks, stride=1)

src/third_part/wav2lip/face_detection/models.py:229

↓ 4 callersMethodclose

(self)

src/third_part/codeformer/video_util.py:84

↓ 4 callersFunctioncreate_layer_basic

(in_chan, out_chan, bnum, stride=1)

src/third_part/facelib/parsing/resnet.py:41

↓ 4 callersMethoderror

(self, message)

src/log_helper.py:146

↓ 4 callersFunctionget_location

(val, length)

src/third_part/facelib/utils/face_restoration_helper.py:19

↓ 4 callersFunctionspectrogram_to_wave

(spec, hop_length, mid_side, mid_side_b2, reverse)

src/third_part/uvr5_pack/lib_v5/spec_utils.py:291

↓ 4 callersFunctiontransform

Generate and affine transformation matrix. Given a set of points, a center, a scale and a targer resolution, the function generates and affin

src/third_part/wav2lip/face_detection/utils.py:56

↓ 3 callersMethod__init__

(self, dim_embd=512, n_head=8, n_layers=9, codebook_size=1024, latent_size=256,

src/third_part/codeformer/codeformer_arch.py:160

↓ 3 callersFunctioncombine_spectrograms

(specs, mp)

src/third_part/uvr5_pack/lib_v5/spec_utils.py:89

↓ 3 callersFunctionconv3x3

3x3 convolution with padding

src/third_part/wav2lip/face_detection/models.py:7

↓ 3 callersFunctionconv_bn1X1

(inp, oup, stride, leaky=0)

src/third_part/facelib/detection/retinaface/retinaface_net.py:19

↓ 3 callersFunctionconv_bn_no_relu

(inp, oup, stride)

src/third_part/facelib/detection/retinaface/retinaface_net.py:12

↓ 3 callersMethoddetect_faces

Params: imgs: BGR image

src/third_part/facelib/detection/retinaface/retinaface.py:193

↓ 3 callersFunctionexact_div

(x, y)

src/third_part/whisperx/utils.py:144

↓ 3 callersFunctionfft_lp_filter

(spec, bin_start, bin_stop)

src/third_part/uvr5_pack/lib_v5/spec_utils.py:427

↓ 3 callersFunctionfindNonreflectiveSimilarity

(uv, xy, options=None)

src/third_part/facelib/detection/matlab_cp2tform.py:60

↓ 3 callersFunctionmake_divisible

(x, divisor)

src/third_part/facelib/detection/yolov5face/utils/general.py:17

↓ 3 callersFunctionmake_pair

(mix_dir, inst_dir)

src/third_part/uvr5_pack/lib_v5/dataset.py:31

↓ 3 callersMethodnms

(self, mode=True)

src/third_part/facelib/detection/yolov5face/models/yolo.py:160

↓ 3 callersFunctionspectrogram_to_image

(spec, mode="magnitude")

src/third_part/uvr5_pack/lib_v5/spec_utils.py:127

↓ 3 callersFunctionwave_to_spectrogram

( wave, hop_length, n_fft, mid_side=False, mid_side_b2=False, reverse=False )

src/third_part/uvr5_pack/lib_v5/spec_utils.py:30

↓ 2 callersMethod__close_handler

关闭handler :param file_handler: 日志记录器

src/log_helper.py:98

↓ 2 callersMethod__detect_faces

(self, inputs)

src/third_part/facelib/detection/retinaface/retinaface.py:146

↓ 2 callersMethod__init__

(self, cin, cout, kernel_size, stride, padding, residual=False, *args, **kwargs)

src/third_part/wav2lip/models/conv.py:6

↓ 2 callersMethod__init_logger_handler

创建日志记录器handler，用于收集日志 :param log_path: 日志文件路径 :return: 日志记录器

src/log_helper.py:43

↓ 2 callersMethod__set_log_formatter

设置日志输出格式-日志文件 :param file_handler: 日志记录器

src/log_helper.py:89

↓ 2 callersMethod__set_log_handler

设置handler级别并添加到logger收集器 :param logger_handler: 日志记录器 :param level: 日志记录器级别

src/log_helper.py:59

↓ 2 callersFunction_amp_to_db

(x)

src/third_part/wav2lip/audio.py:103

↓ 2 callersFunction_execute

( X_mag_pad, roi_size, n_window, device, model, aggressiveness, is_half=True )

src/third_part/uvr5_pack/utils.py:30

↓ 2 callersFunction_normalize

(S)

src/third_part/wav2lip/audio.py:110

↓ 2 callersFunction_stft

(y)

src/third_part/wav2lip/audio.py:57

↓ 2 callersFunction_totensor

(img, bgr2rgb, float32)

src/third_part/facelib/utils/misc.py:70

↓ 2 callersMethodapply

Apply voice activity detection Parameters ---------- file : AudioFile Processed file. hook : callable, op

src/third_part/whisperx/vad.py:209

↓ 2 callersFunctionbox_area

(box)

src/third_part/facelib/detection/yolov5face/utils/general.py:79

↓ 2 callersFunctionbox_iou

Return intersection-over-union (Jaccard index) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format. Arguments:

src/third_part/facelib/detection/yolov5face/utils/general.py:66

↓ 2 callersFunctioncalc_mean_std

Args: feat (numpy): 3D [w h c]s

src/third_part/facelib/utils/misc.py:177

↓ 2 callersFunctioncalc_mean_std

Calculate mean and std for adaptive_instance_normalization. Args: feat (Tensor): 4D tensor. eps (float): A small value added to t

src/third_part/codeformer/codeformer_arch.py:11

↓ 2 callersFunctioncli

()

src/third_part/whisperx/transcribe.py:17

↓ 2 callersFunctionconv3x3

3x3 convolution with padding

src/third_part/facelib/parsing/resnet.py:5

↓ 2 callersMethoddepthwise_conv

(i, o, kernel_size, stride=1, padding=0, bias=False)

src/third_part/facelib/detection/yolov5face/models/common.py:160

↓ 2 callersFunctiondetect

(net, img, device)

src/third_part/wav2lip/face_detection/detection/sfd/detect.py:19

↓ 2 callersMethoddetect_language

(self, audio: np.ndarray)

src/third_part/whisperx/asr.py:245

↓ 2 callersMethodestimate_timestamp_for_word

(self, words, i, next_segment_start_time=None)

src/third_part/whisperx/SubtitlesProcessor.py:48

↓ 2 callersMethodface_detect

(self,images)

src/lipsync.py:214

↓ 2 callersFunctionfft_hp_filter

(spec, bin_start, bin_stop)

src/third_part/uvr5_pack/lib_v5/spec_utils.py:438

↓ 2 callersFunctionformat_timestamp

(seconds: float, is_vtt: bool = False)

src/third_part/whisperx/SubtitlesProcessor.py:11

↓ 2 callersMethodforward

(self, x)

src/third_part/uvr5_pack/lib_v5/nets_new.py:78

↓ 2 callersMethodget_frame

(self)

src/third_part/codeformer/video_util.py:80

↓ 2 callersFunctionget_hop_size

()

src/third_part/wav2lip/audio.py:30

↓ 2 callersFunctionget_largest_face

(det_faces, h, w)

src/third_part/facelib/utils/face_restoration_helper.py:17

↓ 2 callersMethodget_lower_half

(self, face_sequences)

src/third_part/wav2lip/models/wav2lip.py:155

↓ 2 callersFunctionget_reference_facial_points

Function: ---------- get reference 5 key points according to crop settings: 0. Set default crop_size: if default_

src/third_part/facelib/detection/align_trans.py:19

↓ 2 callersFunctionget_similarity_transform

Function: ---------- Find Similarity Transform Matrix 'trans': u = src_pts[:, 0] v = src_pts[:, 1]

src/third_part/facelib/detection/matlab_cp2tform.py:130

↓ 2 callersFunctionimg2tensor

Numpy array to tensor. Args: imgs (list[ndarray] | ndarray): Input images. bgr2rgb (bool): Whether to change bgr to rgb.

src/third_part/facelib/utils/misc.py:57

↓ 2 callersFunctioninit_detection_model

(model_name, half=False, device='cuda')

src/third_part/facelib/detection/__init__.py:14

↓ 2 callersFunctioninterpolate_nans

(x, method='nearest')

src/third_part/whisperx/utils.py:432

↓ 2 callersMethoditerate_result

(self, result: dict, options: dict)

src/third_part/whisperx/utils.py:223

↓ 2 callersFunctionletterbox

(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scale_fill=False, scaleup=True)

src/third_part/facelib/detection/yolov5face/utils/datasets.py:5

↓ 2 callersFunctionload_align_model

(language_code, device, model_name=None, model_dir=None)

src/third_part/whisperx/alignment.py:58

↓ 2 callersFunctionload_model

Load a Whisper model for inference. Args: whisper_arch: str - The name of the Whisper model to load. device: str - The device to l

src/third_part/whisperx/asr.py:259

↓ 2 callersFunctionlog_mel_spectrogram

Compute the log-Mel spectrogram of Parameters ---------- audio: Union[str, np.ndarray, torch.Tensor], shape = (*) The path t

src/third_part/whisperx/audio.py:112

↓ 2 callersFunctionmake_padding

(width, cropsize, offset)

src/third_part/uvr5_pack/lib_v5/dataset.py:118

↓ 2 callersFunctionnms

(dets, thresh)

src/third_part/wav2lip/face_detection/detection/sfd/bbox.py:44

↓ 2 callersFunctionnon_max_suppression

Performs Non-Maximum Suppression (NMS) on inference results Returns: detections with shape: nx6 (x1, y1, x2, y2, conf, cls)

src/third_part/facelib/detection/yolov5face/utils/general.py:168

↓ 2 callersMethodpaste_faces_to_input_image

(self, save_path=None, upsample_img=None, draw_box=False, face_upsampler=None)

src/third_part/facelib/utils/face_restoration_helper.py:370

↓ 2 callersMethodpredict

(self, x_mag, aggressiveness=None)

src/third_part/uvr5_pack/lib_v5/nets.py:116

↓ 2 callersFunctionpreemphasis

(wav, k, preemphasize=True)

src/third_part/wav2lip/audio.py:20

↓ 2 callersFunctionpy_cpu_nms

Pure Python NMS baseline.

src/third_part/facelib/detection/retinaface/retinaface_utils.py:39

next →1–100 of 601, ranked by callers