MCPcopy Create free account

hub / github.com/HumanMLLM/ViSpeak / functions

Functions1,447 in github.com/HumanMLLM/ViSpeak

⨍ Functions 1,447◇ Types & classes 292
↓ 1 callersMethodinitialize_combination_modules
(self, model_args)
vispeak/model/vispeak_arch.py:152
↓ 1 callersMethodinitialize_vision_modules
(self, model_args)
vispeak/model/vispeak_arch.py:54
↓ 1 callersMethodinitialize_vision_tokenizer
(self, model_args, tokenizer)
vispeak/model/vispeak_arch.py:937
↓ 1 callersFunctioninsert_separator
(X, sep)
vispeak/util/mm_utils.py:50
↓ 1 callersFunctionis_api
(x)
VLMEvalKit/scripts/auto_run.py:5
↓ 1 callersFunctionis_equal
(asw: str, gt_asw: str)
VLMEvalKit/vlmeval/dataset/utils/mathv.py:11
↓ 1 callersFunctionis_float_equal
(reference, prediction, include_percentage: bool = False, is_close: float = False)
VLMEvalKit/vlmeval/dataset/mmlongbench.py:112
↓ 1 callersFunctionisfloat
(num)
VLMEvalKit/vlmeval/dataset/mmlongbench.py:187
↓ 1 callersMethodlength_ok
(self, inputs)
VLMEvalKit/vlmeval/api/hf_chat_model.py:159
↓ 1 callersFunctionlist_to_dict
(lst)
VLMEvalKit/vlmeval/dataset/utils/mathvista.py:70
↓ 1 callersFunctionlist_to_dict
(lst)
VLMEvalKit/vlmeval/dataset/utils/mathv.py:96
↓ 1 callersFunctionload_checkpoint
(model: torch.nn.Module, path: str)
vispeak/model/vita_tts/utils.py:10
↓ 1 callersFunctionload_clip_visual_state_dict
( checkpoint_path: str, map_location: str = "cpu", is_openai: bool = False, skip_list: list = [] )
vispeak/model/multimodal_encoder/eva_clip/eva_vit.py:849
↓ 1 callersFunctionload_cmvn
(cmvn_file, is_json)
vispeak/model/vita_tts/encoder/cmvn.py:102
↓ 1 callersFunctionload_cmvn
(filename, is_json)
vispeak/model/multimodal_encoder/whale/cmvn.py:84
↓ 1 callersFunctionload_cmvn_json
(json_cmvn_file)
vispeak/model/multimodal_encoder/whale/cmvn.py:35
↓ 1 callersFunctionload_cmvn_kaldi
(kaldi_cmvn_file)
vispeak/model/multimodal_encoder/whale/cmvn.py:52
↓ 1 callersFunctionload_data
(EVAL_DATA_FILE)
StreamingBench/src/utils/data_execution.py:13
↓ 1 callersMethodload_data
(self, dataset)
VLMEvalKit/vlmeval/dataset/image_base.py:133
↓ 1 callersMethodload_data
(self, dataset)
VLMEvalKit/vlmeval/dataset/text_base.py:65
↓ 1 callersFunctionload_from_hf
(repo_id, filename, subfolder=None)
vispeak/model/builder.py:80
↓ 1 callersMethodload_into_video_and_process
(self, line)
VLMEvalKit/vlmeval/dataset/mvbench.py:292
↓ 1 callersMethodload_model
(self)
vispeak/model/multimodal_encoder/siglip/siglip_encoder.py:22
↓ 1 callersMethodload_model
(self)
vispeak/model/multimodal_encoder/internvit/internvit_encoder.py:25
↓ 1 callersMethodload_model
(self)
vispeak/model/multimodal_encoder/eva_clip/eva_clip_encoder.py:22
↓ 1 callersMethodload_pack_answers
(self, data_raw)
VLMEvalKit/vlmeval/dataset/mmbench_video.py:172
↓ 1 callersMethodload_pretrained_model
(self, model_path, load_8bit=False, load_4bit=False, revision='main')
VLMEvalKit/vlmeval/vlm/transcore_m.py:15
↓ 1 callersFunctionload_state_dict
( checkpoint_path: str, map_location: str = "cpu", model_key: str = "model|module|state_dict",
vispeak/model/multimodal_encoder/eva_clip/eva_vit.py:814
↓ 1 callersMethodload_video
(self, video_path, num_segments=8, resolution=336)
VLMEvalKit/vlmeval/vlm/video_llm/pllava.py:49
↓ 1 callersMethodload_video
(self, video_path, max_frames_num)
VLMEvalKit/vlmeval/vlm/llava/llava.py:503
↓ 1 callersFunctionls
(dirname='.', match=[], mode='all', level=1)
VLMEvalKit/vlmeval/smp/file.py:211
↓ 1 callersFunctionmain
()
data_tools/mmco_collect.py:21
↓ 1 callersFunctionmain
(args)
StreamingBench/src/eval.py:8
↓ 1 callersFunctionmain
(src, dest)
StreamingBench/src/data/move_video.py:5
↓ 1 callersFunctionmain
()
StreamingBench/src/data/modify_video_path.py:22
↓ 1 callersFunctionmain
()
StreamingBench/src/data/count.py:122
↓ 1 callersFunctionmain
()
VLMEvalKit/run.py:42
↓ 1 callersFunctionmake_pad_mask
Make mask tensor containing indices of padded part. See description of make_non_pad_mask. Args: lengths (torch.Tensor): Batch of len
vispeak/model/vita_tts/masks.py:125
↓ 1 callersFunctionmake_pad_mask
(lengths: torch.Tensor, max_len: int = 0)
vispeak/model/multimodal_encoder/whale/utils.py:78
↓ 1 callersFunctionmake_shared_position_ids
(cur_v_start_end, cur_len, shared_v_pid_stride)
vispeak/model/vispeak_arch.py:1004
↓ 1 callersFunctionmake_supervised_data_module
Make dataset and collator for supervised fine-tuning.
vispeak/util/data_utils.py:1142
↓ 1 callersFunctionmaybe_zero_3
(param, ignore_status=False, name=None)
vispeak/train/vispeak_trainer.py:17
↓ 1 callersFunctionmerge_chessboard
x: b * c * h * w Assuming x contains num_split**2 sub-squares concatenated along batch dimension, merge the sub-squares back to the original
vispeak/util/s2wrapper/utils.py:30
↓ 1 callersFunctionmerge_lora
(args)
script/merge_lora_weights.py:8
↓ 1 callersFunctionmerge_txt_files
(input_files, output_file)
data_tools/merge_txt.py:3
↓ 1 callersMethodmessage_to_prompt_embs
(self, message, dataset=None)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer.py:81
↓ 1 callersMethodmessage_to_promptimg
(self, message, dataset=None)
VLMEvalKit/vlmeval/api/base.py:243
↓ 1 callersMethodmessage_to_promptimg
(self, message, dataset=None)
VLMEvalKit/vlmeval/api/sensechat_vision.py:157
↓ 1 callersMethodmoney2chntext
(self)
audio_eval/cn_tn.py:909
↓ 1 callersFunctionmwlines
(lines, fname)
VLMEvalKit/vlmeval/smp/file.py:256
↓ 1 callersFunctionnormalize_nsw
(raw_text)
audio_eval/cn_tn.py:936
↓ 1 callersMethodoutput
(result: Union[str, int])
audio_eval/whisper_normalizer/english.py:176
↓ 1 callersMethodoutput_process
(self, answer)
VLMEvalKit/vlmeval/vlm/mantis.py:127
↓ 1 callersMethodoutput_process
(self, answer)
VLMEvalKit/vlmeval/vlm/llava/llava.py:241
↓ 1 callersFunctionpadding_336
(b)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2_4KHD.py:14
↓ 1 callersFunctionpadding_560
(b)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2d5.py:16
↓ 1 callersFunctionparse_args
()
VLMEvalKit/run.py:13
↓ 1 callersFunctionparse_args
()
VLMEvalKit/scripts/summarize.py:65
↓ 1 callersFunctionparse_line
Parse information from a line in a requirements text file.
VLMEvalKit/setup.py:24
↓ 1 callersFunctionparse_requirements
Parse the package dependencies listed in a requirements file but strips specific versioning information. Args: fname (str): path to r
VLMEvalKit/setup.py:7
↓ 1 callersFunctionparse_score
(review)
VLMEvalKit/vlmeval/dataset/utils/llavabench.py:16
↓ 1 callersMethodpercentage2chntext
(self)
audio_eval/cn_tn.py:932
↓ 1 callersMethodpixel_shuffle
(self, x, scale_factor=0.5)
vispeak/model/multimodal_encoder/internvit/internvit_encoder.py:41
↓ 1 callersMethodpost_build
(self, dataset)
VLMEvalKit/vlmeval/dataset/image_base.py:139
↓ 1 callersMethodpost_build
(self, dataset)
VLMEvalKit/vlmeval/dataset/text_base.py:71
↓ 1 callersMethodpostprocess
(self, s: str)
audio_eval/whisper_normalizer/english.py:417
↓ 1 callersFunctionprefetch_answer
(item)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:232
↓ 1 callersMethodprepare_dataset
(self, dataset)
VLMEvalKit/vlmeval/dataset/video_base.py:83
↓ 1 callersFunctionprepare_file
(file_name)
VLMEvalKit/scripts/mmb_eval_gradio.py:18
↓ 1 callersMethodprepare_inputs
(self, message)
VLMEvalKit/vlmeval/vlm/parrot.py:196
↓ 1 callersMethodprepare_inputs
(self, message)
VLMEvalKit/vlmeval/vlm/ovis.py:113
↓ 1 callersMethodprepare_inputs
(self, message)
VLMEvalKit/vlmeval/vlm/deepseek_vl.py:39
↓ 1 callersMethodprepare_inputs
(self, inputs)
VLMEvalKit/vlmeval/api/claude.py:71
↓ 1 callersMethodprepare_inputs
(self, inputs)
VLMEvalKit/vlmeval/api/hunyuan.py:87
↓ 1 callersMethodprepare_inputs
(self, inputs)
VLMEvalKit/vlmeval/api/gpt.py:153
↓ 1 callersMethodprepare_inputs
(self, inputs)
VLMEvalKit/vlmeval/api/cloudwalk.py:51
↓ 1 callersMethodprepare_inputs
(self, inputs)
VLMEvalKit/vlmeval/api/qwen_vl_api.py:56
↓ 1 callersMethodprepare_inputs_for_generation
( self, input_ids, past_key_values=None, inputs_embeds=None, attention
vispeak/model/language_model/vispeak_qwen2.py:428
↓ 1 callersMethodprepare_inputs_labels_for_multimodal_inference
( self, user_input_ids, position_ids, attention_mask, images, audios, video_audios, pad_token_id, padd
vispeak/model/vispeak_arch.py:759
↓ 1 callersMethodprepare_texts
(self, texts, conv_temp)
VLMEvalKit/vlmeval/vlm/vxverse.py:122
↓ 1 callersMethodprepare_tsv
(self, url, file_md5=None)
VLMEvalKit/vlmeval/dataset/image_base.py:77
↓ 1 callersMethodprepare_tsv
(self, url, file_md5=None)
VLMEvalKit/vlmeval/dataset/text_base.py:29
↓ 1 callersMethodpreproc_image
(self, fname)
VLMEvalKit/vlmeval/vlm/mplug_owl3.py:77
↓ 1 callersFunctionpreprocess_multimodal_offline
( sources: Sequence[str], data_args: DataArguments, patch_num=[1], audio_segment_num=[1],
vispeak/util/data_utils.py:75
↓ 1 callersFunctionpreprocess_qwen2p5_moshi_audio_proactive_data
( sources, tokenizer: transformers.PreTrainedTokenizer, img_token_num, sample_time, use_au
vispeak/util/data_utils.py:408
↓ 1 callersFunctionpreprocess_qwen2p5_moshi_offline_data
( sources, tokenizer: transformers.PreTrainedTokenizer, img_token_num, )
vispeak/util/data_utils.py:202
↓ 1 callersFunctionpreprocess_qwen2p5_moshi_online_data
( sources, tokenizer: transformers.PreTrainedTokenizer, img_token_num, sample_time, proact
vispeak/util/data_utils.py:264
↓ 1 callersMethodprocess_words
(self, words: List[str])
audio_eval/whisper_normalizer/english.py:165
↓ 1 callersMethodqa_template
(self, data)
VLMEvalKit/vlmeval/dataset/mvbench.py:279
↓ 1 callersMethodqa_template
(self, data)
VLMEvalKit/vlmeval/dataset/mvbench.py:499
↓ 1 callersMethodqa_template
(self, data)
VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:353
↓ 1 callersFunctionread_audio
(audio_file)
VLMEvalKit/vlmeval/dataset/videomme.py:30
↓ 1 callersFunctionread_audio
(audio_file)
VLMEvalKit/vlmeval/dataset/mvbench.py:27
↓ 1 callersMethodread_video
(self, video_path, bound=None)
VLMEvalKit/vlmeval/dataset/mvbench.py:520
↓ 1 callersFunctionread_video_pyav
(container, indices)
VLMEvalKit/vlmeval/vlm/video_llm/video_llava.py:11
↓ 1 callersMethodrecognize
( self, speech: torch.Tensor, speech_lengths: torch.Tensor, extra_inputs: Opti
vispeak/model/vita_tts/audioLLM.py:247
↓ 1 callersFunctionreformat_acc
(acc)
VLMEvalKit/scripts/mmb_eval_gradio.py:55
↓ 1 callersFunctionrelaxed_correctness
Calculates relaxed correctness. The correctness tolerates certain error ratio defined by max_relative_change. See https://arxiv.org/pdf/2203.
VLMEvalKit/vlmeval/dataset/utils/vqa_eval.py:172
↓ 1 callersFunctionremove_erhua
去除儿化音词中的儿: 他女儿在那边儿 -> 他女儿在那边
audio_eval/cn_tn.py:1028
↓ 1 callersMethodremove_punctuation
Remove punctuation based on Unicode category.
audio_eval/evaluate_tokenizer.py:43
← previousnext →501–600 of 1,447, ranked by callers