Functions — github.com/HumanMLLM/ViSpeak

CodeHub MCPcopy Create free account

hub / github.com/HumanMLLM/ViSpeak / functions

Functions1,447 in github.com/HumanMLLM/ViSpeak

⨍ Functions 1,447◇ Types & classes 292

↓ 1 callersFunctionfind_all_linear_names

vispeak/train/train.py:159

↓ 1 callersFunctionfind_best_match

Finds the best matching n-gram in the haystack for the given needle. Parameters: needle (str): The string to find. hay (str): The te

VLMEvalKit/vlmeval/dataset/vcr.py:86

↓ 1 callersFunctionfind_closest_aspect_ratio

(aspect_ratio, target_ratios, width, height, image_size)

VLMEvalKit/vlmeval/vlm/mmalaya.py:85

↓ 1 callersFunctionfind_closest_aspect_ratio

(aspect_ratio, target_ratios, width, height, image_size)

VLMEvalKit/vlmeval/vlm/internvl_chat.py:33

↓ 1 callersMethodfind_min_sum_index

Find the index with the minimum sum of a sliding window in the given audio segment and perform operations based on this index.

vispeak/model/vita_tts/decoder/llm2tts.py:70

↓ 1 callersMethodfix_init_weight

vispeak/model/multimodal_encoder/eva_clip/eva_vit.py:717

↓ 1 callersFunctionfloat_cvt

VLMEvalKit/vlmeval/dataset/utils/mmvet.py:46

↓ 1 callersMethodfor_one_step

(self, xin, idx)

vispeak/model/vita_tts/decoder/ticodec/models.py:583

↓ 1 callersMethodfor_one_step_gst

vispeak/model/vita_tts/decoder/ticodec/models.py:617

↓ 1 callersMethodforward

( self, input_ids: torch.LongTensor = None, user_input_ids: torch.LongTensor = None,

vispeak/model/language_model/vispeak_qwen2.py:326

↓ 1 callersMethodfraction2chntext

audio_eval/cn_tn.py:834

↓ 1 callersFunctionframe2img

(img_path_list, font, save_path=None, idx_start=0)

VLMEvalKit/vlmeval/dataset/mmlongbench.py:206

↓ 1 callersFunctiongen_packages_items

VLMEvalKit/setup.py:65

↓ 1 callersFunctiongen_table

(models, datasets)

VLMEvalKit/scripts/summarize.py:72

↓ 1 callersMethodgenerate

The main function to generate the answer. Will call `generate_inner` with the preprocessed input messages. Args: message: raw inp

VLMEvalKit/vlmeval/api/base.py:195

↓ 1 callersMethodgenerate_brief

(self, image_path, text)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2_4KHD.py:142

↓ 1 callersMethodgenerate_brief

(self, image_path, text)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2.py:125

↓ 1 callersMethodgenerate_brief

(self, image_path, text)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2d5.py:198

↓ 1 callersMethodgenerate_inner

(self, message, dataset=None)

VLMEvalKit/vlmeval/vlm/mmalaya.py:40

↓ 1 callersMethodgenerate_inner

(self, message, dataset=None)

VLMEvalKit/vlmeval/vlm/base.py:46

↓ 1 callersMethodgenerate_inner

(self, message, dataset=None)

VLMEvalKit/vlmeval/vlm/deepseek_vl.py:62

↓ 1 callersMethodgenerate_inner_image

(self, message, dataset=None)

VLMEvalKit/vlmeval/vlm/llava/llava.py:420

↓ 1 callersMethodgenerate_inner_video

(self, message, dataset=None)

VLMEvalKit/vlmeval/vlm/llava/llava.py:460

↓ 1 callersMethodgenerate_list

(self, full_inputs, offset=0, **kwargs)

VLMEvalKit/vlmeval/api/hf_chat_model.py:165

↓ 1 callersMethodgenerate_mme

(self, image_path, text)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2_4KHD.py:117

↓ 1 callersMethodgenerate_mme

(self, image_path, text)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2.py:96

↓ 1 callersMethodgenerate_mme

(self, image_path, text)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2d5.py:170

↓ 1 callersMethodgenerate_multichoice

(self, image_path, prompt)

VLMEvalKit/vlmeval/vlm/monkey.py:49

↓ 1 callersMethodgenerate_multichoice

(self, image_path, prompt)

VLMEvalKit/vlmeval/vlm/monkey.py:131

↓ 1 callersMethodgenerate_multichoice

(self, image_path, text, dataset)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2_4KHD.py:124

↓ 1 callersMethodgenerate_multichoice

(self, image_path, text, dataset)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2.py:103

↓ 1 callersMethodgenerate_multichoice

(self, image_path, text, dataset)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2d5.py:177

↓ 1 callersMethodgenerate_str

(self, input, **kwargs)

VLMEvalKit/vlmeval/api/hf_chat_model.py:127

↓ 1 callersMethodgenerate_v1_2

(self, message, dataset=None)

VLMEvalKit/vlmeval/vlm/internvl_chat.py:272

↓ 1 callersMethodgenerate_v1_5

(self, message, dataset=None)

VLMEvalKit/vlmeval/vlm/internvl_chat.py:285

↓ 1 callersMethodgenerate_v2

(self, message, dataset=None)

VLMEvalKit/vlmeval/vlm/internvl_chat.py:312

↓ 1 callersMethodgenerate_vqa

(self, image_path, text)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2_4KHD.py:134

↓ 1 callersMethodgenerate_vqa

(self, image_path, text)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2.py:113

↓ 1 callersMethodgenerate_vqa

(self, image_path, text)

VLMEvalKit/vlmeval/vlm/xcomposer/xcomposer2d5.py:188

↓ 1 callersMethodget_context_emb

(self, conv, model, img_list, answer_prompt=None, print_res=False)

VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:244

↓ 1 callersFunctionget_env

VLMEvalKit/vlmeval/tools.py:293

↓ 1 callersFunctionget_eval

(judge, content)

VLMEvalKit/vlmeval/dataset/utils/llavabench.py:12

↓ 1 callersFunctionget_f1

VLMEvalKit/vlmeval/dataset/slidevqa.py:14

↓ 1 callersFunctionget_f1

VLMEvalKit/vlmeval/dataset/mmlongbench.py:363

↓ 1 callersFunctionget_font

VLMEvalKit/vlmeval/dataset/mmlongbench.py:195

↓ 1 callersFunctionget_gpt4_ICE

VLMEvalKit/vlmeval/dataset/mmlongbench.py:14

↓ 1 callersFunctionget_gpt4_ICE

VLMEvalKit/vlmeval/dataset/utils/mathvista.py:8

↓ 1 callersFunctionget_gpt4_ICE

VLMEvalKit/vlmeval/dataset/utils/mathv.py:38

↓ 1 callersFunctionget_gpu_num

VLMEvalKit/vlmeval/api/hf_chat_model.py:8

↓ 1 callersMethodget_image_token_len

(self, img_path, detail='low')

VLMEvalKit/vlmeval/api/gpt.py:207

↓ 1 callersMethodget_images

(self, return_pil=False)

vispeak/conversation.py:177

↓ 1 callersMethodget_index

(self, max_frame)

VLMEvalKit/vlmeval/dataset/mvbench.py:512

↓ 1 callersMethodget_index

(self, num_frames, num_segments)

VLMEvalKit/vlmeval/vlm/video_llm/pllava.py:61

↓ 1 callersMethodget_index

(self, bound, fps, max_frame, first_idx=0)

VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:214

↓ 1 callersFunctionget_mm_adapter_state_maybe_zero_3

(named_params, keys_to_match)

vispeak/train/train.py:151

↓ 1 callersFunctionget_modality_length_grouped_indices

(lengths, batch_size, world_size, generator=None)

vispeak/train/vispeak_trainer.py:62

↓ 1 callersMethodget_model_conf

(self, model_path)

vispeak/model/vita_tts/decoder/llm2tts.py:32

↓ 1 callersMethodget_model_output

(self, model, video_processor, tokenizer, video, qs)

VLMEvalKit/vlmeval/vlm/video_llm/chat_uni_vi.py:110

↓ 1 callersMethodget_model_output

(self, model, video_processor, tokenizer, video, qs)

VLMEvalKit/vlmeval/vlm/video_llm/llama_vid.py:66

↓ 1 callersMethodget_model_output

(self, model, video_processor, tokenizer, video, qs)

VLMEvalKit/vlmeval/vlm/video_llm/video_llava.py:109

↓ 1 callersMethodget_model_output

(self, model, video_processor, tokenizer, video, qs)

VLMEvalKit/vlmeval/vlm/video_llm/video_chatgpt.py:45

↓ 1 callersFunctionget_peft_state_maybe_zero_3

(named_params, bias)

vispeak/train/train.py:118

↓ 1 callersFunctionget_peft_state_non_lora_maybe_zero_3

(named_params, require_grad_only=True)

vispeak/train/train.py:143

↓ 1 callersFunctionget_prompt

VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:22

↓ 1 callersFunctionget_prompt2

VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:32

↓ 1 callersMethodget_sinusoid_encoding_table

Sinusoid position encoding table

VLMEvalKit/vlmeval/vlm/video_llm/videochat2.py:165

↓ 1 callersMethodget_token_len

VLMEvalKit/vlmeval/api/gpt.py:227

↓ 1 callersFunctionget_value

(value_string, use_zeros=True)

audio_eval/cn_tn.py:659

↓ 1 callersFunctionget_version

VLMEvalKit/docs/en/conf.py:34

↓ 1 callersFunctionget_version

VLMEvalKit/docs/zh-CN/conf.py:34

↓ 1 callersFunctionget_video_frame

( video_path, max_frames=MAX_IMAGE_LENGTH, min_frames=MIN_IMAGE_LENGTH, video_framerate=1,

data_tools/statistics_token_num_patch_video.py:84

↓ 1 callersMethodget_vision_tower

vispeak/model/vispeak_arch.py:188

↓ 1 callersFunctionget_wav_duration

data_tools/statistics_token_num_frameCat.py:74

↓ 1 callersFunctionget_wav_duration

data_tools/check_audio_lost.py:30

↓ 1 callersFunctionget_wav_duration

data_tools/statistics_token_num.py:37

↓ 1 callersFunctionget_wav_duration

data_tools/concat_data_patch_qwen.py:60

↓ 1 callersFunctionget_wav_duration

data_tools/statistics_token_num_patch.py:68

↓ 1 callersFunctionget_wav_duration

data_tools/statistics_token_num_patch_video.py:78

↓ 1 callersFunctionget_wav_duration

data_tools/statistics_audio_duration.py:26

↓ 1 callersFunctionh2r

VLMEvalKit/vlmeval/smp/misc.py:44

↓ 1 callersMethodimage_to_base64

(self, image_path)

VLMEvalKit/vlmeval/api/sensechat_vision.py:65

↓ 1 callersFunctionimg_root_map

VLMEvalKit/vlmeval/dataset/image_base.py:6

↓ 1 callersMethodinfer

(self, xs_pad, buffer, buffer_index, buffer_out, pe_index)

vispeak/model/vita_tts/encoder/encoder.py:149

↓ 1 callersMethodinfer

(self, hidden, top_k, prefix, penalty_window_size, penalty, max_tokens=1000)

vispeak/model/vita_tts/decoder/decoder.py:314

↓ 1 callersFunctioninfer_data

(model_name, work_dir, dataset, out_file, nframe=8, pack=False, verbose=False, api_nproc=4)

VLMEvalKit/vlmeval/inference_video.py:49

↓ 1 callersFunctioninfer_data

(model_name, work_dir, dataset, out_file, verbose=False, api_nproc=4)

VLMEvalKit/vlmeval/inference_mt.py:77

↓ 1 callersFunctioninfer_data

(model_name, work_dir, dataset, out_file, verbose=False, api_nproc=4)

VLMEvalKit/vlmeval/inference.py:69

↓ 1 callersFunctioninfer_data_api

(work_dir, model_name, dataset, nframe=8, pack=False, samples_dict={}, api_nproc=4)

VLMEvalKit/vlmeval/inference_video.py:21

↓ 1 callersFunctioninfer_data_api

(work_dir, model_name, dataset, index_set=None, api_nproc=4, ignore_failed=False)

VLMEvalKit/vlmeval/inference_mt.py:40

↓ 1 callersFunctioninfer_data_api

(work_dir, model_name, dataset, index_set=None, api_nproc=4, ignore_failed=False)

VLMEvalKit/vlmeval/inference.py:21

↓ 1 callersFunctioninfer_data_job

(model, work_dir, model_name, dataset, verbose=False, api_nproc=4, ignore_failed=False)

VLMEvalKit/vlmeval/inference.py:143

↓ 1 callersFunctioninfer_data_job_mt

(model, work_dir, model_name, dataset, verbose=False, api_nproc=4, ignore_failed=False)

VLMEvalKit/vlmeval/inference_mt.py:151

↓ 1 callersFunctioninfer_data_job_video

( model, work_dir, model_name, dataset, nframe=8, pack=False,

VLMEvalKit/vlmeval/inference_video.py:105

↓ 1 callersFunctioninit_encoder_llm

vispeak/model/vita_tts/utils.py:29

↓ 1 callersMethodinit_kv_cache_prefix

vispeak/model/vita_tts/decoder/decoder.py:121

↓ 1 callersFunctioninit_model

vispeak/model/multimodal_encoder/whale/init_model.py:183

↓ 1 callersFunctioninit_omni_lmm

VLMEvalKit/vlmeval/vlm/omnilmm.py:16

↓ 1 callersMethodinit_pre_nn

vispeak/model/vita_tts/decoder/decoder.py:156

↓ 1 callersFunctioninitialize

VLMEvalKit/vlmeval/dataset/vcr.py:12

↓ 1 callersMethodinitialize_audio_modules

(self, model_args)

vispeak/model/vispeak_arch.py:87

← previous next →401–500 of 1,447, ranked by callers