MCPcopy Create free account

hub / github.com/VITA-MLLM/VITA-Audio / functions

Functions566 in github.com/VITA-MLLM/VITA-Audio

⨍ Functions 566◇ Types & classes 121↳ Endpoints 4
Methodinference
( self, data_in, data_lengths=None, key: list = ["wav_file_tmp_name"],
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_sensevoice.py:861
Functioninit_weights
(m)
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/resampler_projector.py:30
Methodis_contiguous
(self)
vita_audio/data/processor/audio_processor.py:71
Methodis_discrete
(self)
vita_audio/data/processor/audio_processor.py:67
Methodkeys
(self)
evaluation/compute-wer.py:239
Methodload_cmvn
(self)
web/vad.py:150
Functionload_data_one
(data_file, output_dir)
vita_audio/data/dataset_base.py:326
Functionload_json_A
(data_file)
vita_audio/data/dataset_base.py:280
Functionload_json_B
(data_file)
vita_audio/data/dataset_base.py:289
Functionload_json_C
(data_file)
vita_audio/data/dataset_base.py:296
Functionmake_inputs_require_grad
(module, input, output)
tools/finetune_sts_v4_48_3.py:533
Methodpost_process_history
(self, history)
web/vad.py:180
Functionpredict
(_chatbot, task_history, task)
web_demo.py:65
Methodprepare_for_tokenization
(self, text, **kwargs)
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/tokenization_qwen2.py:339
Methodprepare_for_tokenization
(self, text, **kwargs)
vita_audio/models/qwen2_v4_48_3/tokenization_qwen2.py:337
Methodprepare_for_tokenization
(self, text, **kwargs)
vita_audio/models/qwen2_mtp_v4_48_3/tokenization_qwen2.py:339
Functionpreprocess_logits_for_metrics
(logits, labels)
tools/finetune_sts_v4_48_3.py:655
Methodprint_info
(self)
web/pool.py:53
Methodprint_info
(self)
web/pool.py:92
Methodput
Receives tokens, decodes them, and prints them to stdout as soon as they form entire words.
tools/inference_sts.py:85
Methodput
Receives tokens, decodes them, and prints them to stdout as soon as they form entire words.
tools/inference_sts.py:140
Methodput
Add an item to the queue in a thread-safe manner. Parameters: - item (any): The item to be added to the queue. Retu
web/queue.py:100
Methodrelease
(self, obj)
web/pool.py:88
Methodrelease
(self)
web/parms.py:90
Functionreset_state
(task_history)
web_demo.py:246
Functionreset_user_input
()
web_demo.py:242
Functionsafe_globals
()
tools/trainer_v4_48_3.py:274
Methodsave_video_frames
(self, vid_path, max_fps=1, num_frames=8)
vita_audio/data/processor/image_processor.py:86
Methodsave_vocabulary
(self, save_directory: str, filename_prefix: Optional[str] = None)
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/tokenization_qwen2_fast.py:132
Methodsave_vocabulary
(self, save_directory: str, filename_prefix: Optional[str] = None)
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/tokenization_qwen2.py:310
Methodsave_vocabulary
(self, save_directory: str, filename_prefix: Optional[str] = None)
vita_audio/models/qwen2_v4_48_3/tokenization_qwen2_fast.py:132
Methodsave_vocabulary
(self, save_directory: str, filename_prefix: Optional[str] = None)
vita_audio/models/qwen2_v4_48_3/tokenization_qwen2.py:308
Methodsave_vocabulary
(self, save_directory: str, filename_prefix: Optional[str] = None)
vita_audio/models/qwen2_mtp_v4_48_3/tokenization_qwen2_fast.py:132
Methodsave_vocabulary
(self, save_directory: str, filename_prefix: Optional[str] = None)
vita_audio/models/qwen2_mtp_v4_48_3/tokenization_qwen2.py:310
Functionsend_pcm
Sends PCM audio data to the dialogue system for processing. Parameters: - sid (str): The session ID of the user.
web_demo_stream.py:373
Methodset_decoder
(self, decoder)
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:866
Methodset_decoder
(self, decoder)
vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:758
Methodset_decoder
(self, decoder)
vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:813
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:546
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:857
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:1378
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:1481
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:1563
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:498
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:749
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:882
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:985
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:1067
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:540
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:804
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:1321
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:1424
Methodset_input_embeddings
(self, value)
vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:1506
Methodset_output_embeddings
(self, new_embeddings)
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:863
Methodset_output_embeddings
(self, new_embeddings)
vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:755
Methodset_output_embeddings
(self, new_embeddings)
vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:810
Methodset_prompt
(self, prompt)
web/parms.py:53
Functionsnac
()
tools/get_neural_audio_codecs.py:220
Functionsparktts
()
tools/get_neural_audio_codecs.py:300
Functiontext_audio_interval_old
(input_ids, AUD_START_ID, AUD_END_ID, text_audio_interval_ratio)
vita_audio/data/dataset_deepseek.py:827
Functiontext_audio_interval_old
(input_ids, AUD_START_ID, AUD_END_ID, text_audio_interval_ratio)
vita_audio/data/processor/audio_processor.py:146
Methodtraining_step
Perform a training step on a batch of inputs. Subclass and override to inject custom behavior. Args: model (`nn
tools/trainer_v4_48_3.py:1093
Methodvocab_size
(self)
vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/tokenization_qwen2.py:213
Methodvocab_size
(self)
vita_audio/models/qwen2_v4_48_3/tokenization_qwen2.py:211
Methodvocab_size
(self)
vita_audio/models/qwen2_mtp_v4_48_3/tokenization_qwen2.py:213
Functionxcodec2
()
tools/get_neural_audio_codecs.py:77
← previous501–566 of 566, ranked by callers