MCPcopy Create free account

hub / github.com/HumanMLLM/ViSpeak / functions

Functions1,447 in github.com/HumanMLLM/ViSpeak

⨍ Functions 1,447◇ Types & classes 292
↓ 2 callersFunctionload_video
(video_path)
VLMEvalKit/vlmeval/vlm/video_llm/llama_vid.py:14
↓ 2 callersFunctionlocalize_df
(data, dname, nproc=32)
VLMEvalKit/vlmeval/smp/file.py:34
↓ 2 callersFunctionmcq_circular_eval
(model, data, meta, nproc, result_file, dataset_name=None)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:375
↓ 2 callersFunctionmmqa_display
(question, target_size=512)
VLMEvalKit/vlmeval/smp/vlm.py:57
↓ 2 callersFunctionokn
(o, n=4)
VLMEvalKit/vlmeval/tools.py:163
↓ 2 callersFunctionparse_require_file
(fpath)
VLMEvalKit/setup.py:57
↓ 2 callersMethodpre_nn_forward
(self, hidden, hidden_lens)
vispeak/model/vita_tts/decoder/decoder.py:162
↓ 2 callersFunctionprefetch_circular_group
(sub_data, verbose=False)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:275
↓ 2 callersMethodprepare_inputs_labels_for_multimodal
( self, input_ids, user_input_ids, position_ids, attention_mask, past_key_values, labels, images, audi
vispeak/model/vispeak_arch.py:359
↓ 2 callersMethodprepare_itlist
(self, inputs)
VLMEvalKit/vlmeval/api/claude.py:44
↓ 2 callersMethodprepare_itlist
(self, inputs)
VLMEvalKit/vlmeval/api/hunyuan.py:67
↓ 2 callersMethodprepare_itlist
(self, inputs)
VLMEvalKit/vlmeval/api/gpt.py:133
↓ 2 callersMethodprepare_itlist
(self, inputs)
VLMEvalKit/vlmeval/api/qwen_vl_api.py:40
↓ 2 callersMethodpreproc_content
Convert the raw input messages to a list of dicts. Args: inputs: raw input messages. Returns: list(dict): Th
VLMEvalKit/vlmeval/vlm/base.py:64
↓ 2 callersMethodpreproc_content
Convert the raw input messages to a list of dicts. Args: inputs: raw input messages. Returns: list(dict): Th
VLMEvalKit/vlmeval/api/base.py:104
↓ 2 callersMethodprocess
(self, wav, start_time=None, end_time=None)
vispeak/model/multimodal_encoder/whale/init_model.py:35
↓ 2 callersMethodprocess_answer_prefix
(self, answer, prefixes)
VLMEvalKit/vlmeval/vlm/parrot.py:131
↓ 2 callersFunctionprocess_punctuation
(inText)
VLMEvalKit/vlmeval/smp/misc.py:26
↓ 2 callersMethodremove_side_quote
(s, syms=[',', '"', "'"])
VLMEvalKit/vlmeval/dataset/mmbench_video.py:140
↓ 2 callersFunctionremove_sp
(text, language)
audio_eval/eval_asr.py:159
↓ 2 callersFunctionreport_acc_MMT
(df)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:94
↓ 2 callersFunctionrotate_half
(x)
vispeak/model/multimodal_encoder/eva_clip/eva_vit.py:45
↓ 2 callersMethodset_dump_image
(self, dump_image_func)
VLMEvalKit/vlmeval/vlm/base.py:39
↓ 2 callersMethodset_max_num
(self, dataset)
VLMEvalKit/vlmeval/vlm/internvl_chat.py:260
↓ 2 callersMethodslow_fast_pooling
(self, temp_img_feats)
vispeak/model/vispeak_arch.py:298
↓ 2 callersMethodsplit_MMMU
(msgs)
VLMEvalKit/vlmeval/dataset/image_mcq.py:274
↓ 2 callersFunctionsubsequent_chunk_mask
Create mask for subsequent steps (size, size) with chunk size, this is for streaming encoder Args: size (int): size of mask
vispeak/model/vita_tts/masks.py:23
↓ 2 callersFunctionsubsequent_chunk_mask
( size: int, ck_size: int, num_l_cks: int = -1, device: torch.device = torch.device("cpu"), )
vispeak/model/multimodal_encoder/whale/utils.py:88
↓ 2 callersMethodtelephone2chntext
(self, fixed=False)
audio_eval/cn_tn.py:804
↓ 2 callersFunctionto_value
Convert the string to Value object. Args: original_string (basestring): Original string corenlp_value (basestring): Optional valu
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:406
↓ 2 callersFunctionto_value_list
Convert a list of strings to a list of Values Args: original_strings (list[basestring]) corenlp_values (list[basestring or None])
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:435
↓ 2 callersFunctiontokenize
Tokenize the text and return the tokens. Parameters: text (str): The text to tokenize. language (str): The language of the text.
VLMEvalKit/vlmeval/dataset/vcr.py:69
↓ 2 callersMethodtokenize
(self, sent: str)
audio_eval/evaluate_tokenizer.py:49
↓ 2 callersMethodtransformer_infer
(self, inputs_embeds, cache_position, past_key_values)
vispeak/model/vita_tts/decoder/decoder.py:294
↓ 2 callersFunctiontsv_unescape_list
Unescape a list in the TSV file. List items are joined with vertical bars (0x5C) Args: x (str or unicode) Returns: a list
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:491
↓ 2 callersFunctionversion_cmp
(v1, v2, op='eq')
VLMEvalKit/vlmeval/smp/misc.py:189
↓ 2 callersFunctionzero_template
(crossed_text)
VLMEvalKit/vlmeval/dataset/vcr.py:55
↓ 1 callersFunctionCHECK
(val)
VLMEvalKit/vlmeval/tools.py:258
↓ 1 callersFunctionCIRCULAR
(inp)
VLMEvalKit/vlmeval/tools.py:148
↓ 1 callersFunctionDLIST
(lvl)
VLMEvalKit/vlmeval/tools.py:114
↓ 1 callersFunctionDUDE_acc
(result_file)
VLMEvalKit/vlmeval/dataset/dude.py:13
↓ 1 callersFunctionEVAL
(dataset_name, data_file)
VLMEvalKit/vlmeval/tools.py:346
↓ 1 callersFunctionGPT_context_window
(model)
VLMEvalKit/vlmeval/api/gpt.py:11
↓ 1 callersFunctionHD_transform
(img, im_num=16)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2_4KHD.py:26
↓ 1 callersFunctionHallusion_rating
(data_file)
VLMEvalKit/vlmeval/dataset/utils/yorn.py:50
↓ 1 callersFunctionLLaVABench_score
(data)
VLMEvalKit/vlmeval/dataset/utils/llavabench.py:55
↓ 1 callersFunctionMATH_V_acc
(result_file)
VLMEvalKit/vlmeval/dataset/utils/mathv.py:143
↓ 1 callersFunctionMLIST
(lvl, size='all')
VLMEvalKit/vlmeval/tools.py:119
↓ 1 callersFunctionMMBenchOfficialServer
(dataset_name)
VLMEvalKit/vlmeval/smp/file.py:77
↓ 1 callersFunctionMME_rating
(data_file)
VLMEvalKit/vlmeval/dataset/utils/yorn.py:4
↓ 1 callersFunctionMMLongBench_acc
(result_file)
VLMEvalKit/vlmeval/dataset/mmlongbench.py:371
↓ 1 callersFunctionMMMU_preproc
(data)
VLMEvalKit/vlmeval/dataset/utils/multiple_choice.py:52
↓ 1 callersFunctionMMMU_result_transfer
(result_path)
VLMEvalKit/vlmeval/utils/result_transfer.py:8
↓ 1 callersFunctionMMTBench_result_transfer
(eval_file, dataset='default', **judge_kwargs)
VLMEvalKit/vlmeval/utils/result_transfer.py:31
↓ 1 callersFunctionMMVet_acc
(result_file)
VLMEvalKit/vlmeval/dataset/utils/mmvet.py:69
↓ 1 callersFunctionMathVista_acc
(result_file)
VLMEvalKit/vlmeval/dataset/utils/mathvista.py:124
↓ 1 callersFunctionPOPE_rating
(data_file)
VLMEvalKit/vlmeval/dataset/utils/yorn.py:102
↓ 1 callersMethodRun
(self, file, inp, start_time, end_time, question_time, omni=False, proactive=False)
StreamingBench/src/model/ViSpeak.py:21
↓ 1 callersFunctionSlideVQA_acc
(result_file)
VLMEvalKit/vlmeval/dataset/slidevqa.py:25
↓ 1 callersFunctionStreamingBenchEval
(data, MODEL, output_path, video_root)
StreamingBench/src/benchmark/StreamingBench.py:34
↓ 1 callersFunctionStreamingBenchEval
(data, MODEL, output_path, video_root)
StreamingBench/src/benchmark/StreamingBenchOmni.py:34
↓ 1 callersFunctionStreamingBenchInit
(data)
StreamingBench/src/benchmark/StreamingBench.py:31
↓ 1 callersFunctionStreamingBenchInit
(data)
StreamingBench/src/benchmark/StreamingBenchOmni.py:31
↓ 1 callersFunctionStreamingBenchProactiveEval
(data, MODEL, output_path, video_root)
StreamingBench/src/benchmark/StreamingBenchProactive.py:28
↓ 1 callersFunctionStreamingBenchProactiveInit
(data)
StreamingBench/src/benchmark/StreamingBenchProactive.py:25
↓ 1 callersFunctionStreamingBenchSQAEval
(data, MODEL, output_path, video_root)
StreamingBench/src/benchmark/StreamingBenchSQA.py:35
↓ 1 callersFunctionStreamingBenchSQAInit
(data)
StreamingBench/src/benchmark/StreamingBenchSQA.py:32
↓ 1 callersMethodViSpeak_Init
(self,)
StreamingBench/src/model/ViSpeak.py:27
↓ 1 callersMethodViSpeak_Run
(self, file, inp, start_time, end_time, question_time, omni=False, proactive=False)
StreamingBench/src/model/ViSpeak.py:50
↓ 1 callersFunctionYOrN_match_prompt
(line)
VLMEvalKit/vlmeval/dataset/utils/yorn.py:166
↓ 1 callersMethod__init__
Construct an Encoder object.
vispeak/model/vita_tts/encoder/transformer.py:156
↓ 1 callersMethod__init__
Initialize transducer modules. Args: idim (int): dimension of inputs odim (int): dimension of outputs arg
vispeak/model/vita_tts/decoder/decoder.py:60
↓ 1 callersMethod__init__
(self, config_path, ckpt_path, with_encoder=False)
vispeak/model/vita_tts/decoder/ticodec/vqvae.py:16
↓ 1 callersMethod__init__
(self, config: Qwen2Config)
vispeak/model/language_model/vispeak_qwen2.py:290
↓ 1 callersMethod__init__
(self, vision_tower, args, delay_load=False)
vispeak/model/multimodal_encoder/siglip/siglip_encoder.py:9
↓ 1 callersMethod__init__
Construct an Encoder object.
vispeak/model/multimodal_encoder/whale/module/component/mamba.py:101
↓ 1 callersMethod__init__
Construct an Encoder object.
vispeak/model/multimodal_encoder/whale/module/component/transformer.py:239
↓ 1 callersMethod__init__
(self)
vispeak/model/multimodal_encoder/eva_clip/eva_clip_encoder.py:63
↓ 1 callersMethod__init__
(self)
vispeak/model/multimodal_encoder/eva_clip/eva_clip_processors.py:14
↓ 1 callersMethod__init__
(self)
audio_eval/whisper_normalizer/english.py:466
↓ 1 callersMethod__init__
(self, func)
VLMEvalKit/vlmeval/utils/mp_util.py:16
↓ 1 callersMethod__init__
(self, dataset='MVBench', pack=False)
VLMEvalKit/vlmeval/dataset/mvbench.py:72
↓ 1 callersMethod__init__
(self, model_path='internlm/internlm-xcomposer-vl-7b', **kwargs)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer.py:28
↓ 1 callersMethod__init__
(self, model_path='OpenGVLab/VideoChat2_HD_stage4_Mistral_7B', root='./Ask-Anything', config_
VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:64
↓ 1 callersFunction__padding__
(image)
VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2.py:12
↓ 1 callersMethod__str__
(self)
audio_eval/cn_tn.py:405
↓ 1 callersMethod__str__
(self)
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:273
↓ 1 callersMethod__str__
(self)
VLMEvalKit/vlmeval/dataset/utils/tablevqabench.py:307
↓ 1 callersMethod_add_bos_eos
(self, bos, eos, inputs_embeds, attention_mask, target=None)
vispeak/model/multimodal_encoder/whale/init_model.py:162
↓ 1 callersFunction_build_vision_tower
(vision_tower_path: str, embed_dim: int, vision_cfg: CLIPVisionCfg)
vispeak/model/multimodal_encoder/eva_clip/eva_vit.py:905
↓ 1 callersMethod_flash_attn
(self, x, key_padding_mask=None, need_weights=False)
vispeak/model/multimodal_encoder/internvit/modeling_intern_vit.py:179
↓ 1 callersMethod_get_context_length
(self, model, model_path)
VLMEvalKit/vlmeval/api/hf_chat_model.py:36
↓ 1 callersMethod_get_context_length_robust
(self, model, model_path)
VLMEvalKit/vlmeval/api/hf_chat_model.py:50
↓ 1 callersMethod_get_local_indices
(total_size, world_size, rank)
audio_eval/eval_asr.py:144
↓ 1 callersMethod_get_pos_embed
(self, pos_embed, H, W)
vispeak/model/multimodal_encoder/internvit/modeling_intern_vit.py:92
↓ 1 callersFunction_get_rawvideo_dec
( video_path, image_processor, max_frames=64, image_resolution=224, video_framerate=1,
VLMEvalKit/vlmeval/vlm/video_llm/chat_uni_vi.py:14
↓ 1 callersFunction_load_json_cmvn
Load the json format cmvn stats file and calculate cmvn Args: json_cmvn_file: cmvn stats file in json format Returns: a num
vispeak/model/vita_tts/encoder/cmvn.py:37
↓ 1 callersFunction_load_kaldi_cmvn
Load the kaldi format cmvn stats file and calculate cmvn Args: kaldi_cmvn_file: kaldi text style global cmvn file, which is
vispeak/model/vita_tts/encoder/cmvn.py:61
↓ 1 callersMethod_model_init
(self)
OVO-Bench/models/ViSpeak.py:30
↓ 1 callersMethod_naive_attn
(self, x)
vispeak/model/multimodal_encoder/internvit/modeling_intern_vit.py:158
← previousnext →201–300 of 1,447, ranked by callers