Types & classes — github.com/VITA-MLLM/VITA-Audio

CodeHub MCPcopy Create free account

hub / github.com/VITA-MLLM/VITA-Audio / types & classes

Types & classes121 in github.com/VITA-MLLM/VITA-Audio

⨍ Functions 566◇ Types & classes 121↳ Endpoints 4

↓ 5 callersClassQwen2RMSNorm

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:253

↓ 5 callersClassQwen2RMSNorm

vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:250

↓ 4 callersClassLayerNorm

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_sensevoice.py:343

↓ 4 callersClassQwen2Model

Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`Qwen2DecoderLayer`] Args: config: Qwen2Config

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:516

↓ 4 callersClassQwen2Model

Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`Qwen2DecoderLayer`] Args: config: Qwen2Config

vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:471

↓ 4 callersClassQwen2Model

Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`Qwen2DecoderLayer`] Args: config: Qwen2Config

vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:513

↓ 3 callersClassEncoderLayerSANM

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_sensevoice.py:370

↓ 3 callersClassQwen2RMSNorm

vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:208

↓ 2 callersClassVADIterator

↓ 1 callersClassASRDataset

evaluation/evaluate_asr.py:33

↓ 1 callersClassAudioEncoder

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_sensevoice.py:1065

↓ 1 callersClassAudioProcessor

vita_audio/data/processor/audio_processor.py:12

↓ 1 callersClassBenchmarkIteratorStreamer

tools/inference_sts.py:128

↓ 1 callersClassCalculator

evaluation/compute-cer.py:91

↓ 1 callersClassCalculator

evaluation/compute-wer.py:85

↓ 1 callersClassCosyVoice2Tokenizer

vita_audio/tokenizer_cosyvoice2.py:66

↓ 1 callersClassGLM4VoiceTokenizer

vita_audio/tokenizer_glm4voice.py:77

↓ 1 callersClassGlobalParams

web/parms.py:25

↓ 1 callersClassImageProcessor

vita_audio/data/processor/image_processor.py:20

↓ 1 callersClassInferenceSampler

evaluation/evaluate_seedtts.py:157

↓ 1 callersClassInferenceSampler

evaluation/evaluate_asr.py:127

↓ 1 callersClassInferenceSampler

evaluation/evaluate_libritts.py:84

↓ 1 callersClassInferenceSampler

evaluation/evaluate_sqa.py:130

↓ 1 callersClassPCMQueue

web/queue.py:14

↓ 1 callersClassQwen2Attention

Multi-headed attention from 'Attention Is All You Need' paper

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:177

↓ 1 callersClassQwen2Attention

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modular_qwen2.py:38

↓ 1 callersClassQwen2Attention

Multi-headed attention from 'Attention Is All You Need' paper

vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:132

↓ 1 callersClassQwen2Attention

vita_audio/models/qwen2_v4_48_3/modular_qwen2.py:38

↓ 1 callersClassQwen2Attention

Multi-headed attention from 'Attention Is All You Need' paper

vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:174

↓ 1 callersClassQwen2Attention

vita_audio/models/qwen2_mtp_v4_48_3/modular_qwen2.py:38

↓ 1 callersClassQwen2DecoderLayer

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:273

↓ 1 callersClassQwen2DecoderLayer

vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:228

↓ 1 callersClassQwen2DecoderLayer

vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:270

↓ 1 callersClassQwen2MLP

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:89

↓ 1 callersClassQwen2MLP

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modular_qwen2.py:30

↓ 1 callersClassQwen2MLP

vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:44

↓ 1 callersClassQwen2MLP

vita_audio/models/qwen2_v4_48_3/modular_qwen2.py:30

↓ 1 callersClassQwen2MLP

vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:86

↓ 1 callersClassQwen2MLP

vita_audio/models/qwen2_mtp_v4_48_3/modular_qwen2.py:30

↓ 1 callersClassQwen2RotaryEmbedding

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:330

↓ 1 callersClassQwen2RotaryEmbedding

vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:285

↓ 1 callersClassQwen2RotaryEmbedding

vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:327

↓ 1 callersClassResamplerProjector

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/resampler_projector.py:8

↓ 1 callersClassS2SInference

tools/inference_sts.py:190

↓ 1 callersClassSNACTokenizer

vita_audio/tokenizer_snac.py:68

↓ 1 callersClassSTSDataset

evaluation/evaluate_sqa.py:34

↓ 1 callersClassSeedTTSDataset

evaluation/evaluate_seedtts.py:32

↓ 1 callersClassSenseVoiceGLM4VoiceTokenizer

vita_audio/tokenizer_sensevoice_glm4voice.py:83

↓ 1 callersClassSenseVoiceSparkTTSTokenizer

vita_audio/tokenizer_sensevoice_sparktts.py:70

↓ 1 callersClassSinusoidalPositionEncoder

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_sensevoice.py:93

↓ 1 callersClassTTSDataset

evaluation/evaluate_libritts.py:33

↓ 1 callersClassTextAudioIteratorStreamer

web_demo_stream.py:162

↓ 1 callersClassTextAudioIteratorStreamer

tools/inference_sts.py:71

↓ 1 callersClassThreadSafeQueue

web/queue.py:86

↓ 1 callersClassTrainer

tools/trainer_v4_48_3.py:384

↓ 1 callersClassWakeupAndVAD

↓ 1 callersClassinferencePipelineObject

ClassBaseDataset

vita_audio/data/dataset_base.py:26

ClassCosyVoice2Dataset

vita_audio/data/dataset_cosyvoice2.py:24

ClassDataCollatorForSupervisedDataset

vita_audio/data/data_collator.py:19

ClassDataTrainingArguments

Arguments pertaining to what data we are going to input our model for training and eval.

tools/finetune_sts_v4_48_3.py:178

ClassDeepSeekDataset

vita_audio/data/dataset_deepseek.py:24

ClassHunyuanDataset

vita_audio/data/dataset_hunyuan.py:24

ClassKwargsForCausalLM

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:831

ClassKwargsForCausalLM

vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:730

ClassKwargsForCausalLM

vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:778

ClassLlama3Dataset

vita_audio/data/dataset_llama3.py:24

ClassMistralDataset

vita_audio/data/dataset_mistral.py:22

ClassModelArguments

Arguments pertaining to which model/config/tokenizer we are going to fine-tune, or train from scratch.

tools/finetune_sts_v4_48_3.py:55

ClassMultiHeadedAttentionSANM

Multi-Head Attention layer. Args: n_head (int): The number of heads. n_feat (int): The number of features. dropout_rate (

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_sensevoice.py:149

ClassPooledCodecTTSObject

ClassPositionwiseFeedForward

Positionwise feed forward layer. Args: idim (int): Input dimenstion. hidden_units (int): The number of hidden units. drop

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_sensevoice.py:126

ClassQwen2Config

r""" This is the configuration class to store the configuration of a [`Qwen2Model`]. It is used to instantiate a Qwen2 model according to the

vita_audio/models/qwen2_v4_48_3/configuration_qwen2.py:25

ClassQwen2Dataset

vita_audio/data/dataset_qwen2.py:24

ClassQwen2DecoderLayer

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modular_qwen2.py:105

ClassQwen2DecoderLayer

vita_audio/models/qwen2_v4_48_3/modular_qwen2.py:105

ClassQwen2DecoderLayer

vita_audio/models/qwen2_mtp_v4_48_3/modular_qwen2.py:105

ClassQwen2ForCausalLM

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modular_qwen2.py:121

ClassQwen2ForCausalLM

vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:733

ClassQwen2ForCausalLM

vita_audio/models/qwen2_v4_48_3/modular_qwen2.py:121

ClassQwen2ForCausalLM

vita_audio/models/qwen2_mtp_v4_48_3/modular_qwen2.py:121

ClassQwen2ForQuestionAnswering

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:1549

ClassQwen2ForQuestionAnswering

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modular_qwen2.py:133

ClassQwen2ForQuestionAnswering

vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:1053

ClassQwen2ForQuestionAnswering

vita_audio/models/qwen2_v4_48_3/modular_qwen2.py:133

ClassQwen2ForQuestionAnswering

vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:1492

ClassQwen2ForQuestionAnswering

vita_audio/models/qwen2_mtp_v4_48_3/modular_qwen2.py:133

ClassQwen2ForSequenceClassification

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:1365

ClassQwen2ForSequenceClassification

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modular_qwen2.py:125

ClassQwen2ForSequenceClassification

vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:869

ClassQwen2ForSequenceClassification

vita_audio/models/qwen2_v4_48_3/modular_qwen2.py:125

ClassQwen2ForSequenceClassification

vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:1308

ClassQwen2ForSequenceClassification

vita_audio/models/qwen2_mtp_v4_48_3/modular_qwen2.py:125

ClassQwen2ForTokenClassification

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modeling_qwen2.py:1461

ClassQwen2ForTokenClassification

vita_audio/models/qwen2_mtp_sensevoice_v4_48_3/modular_qwen2.py:129

ClassQwen2ForTokenClassification

vita_audio/models/qwen2_v4_48_3/modeling_qwen2.py:965

ClassQwen2ForTokenClassification

vita_audio/models/qwen2_v4_48_3/modular_qwen2.py:129

ClassQwen2ForTokenClassification

vita_audio/models/qwen2_mtp_v4_48_3/modeling_qwen2.py:1404

ClassQwen2ForTokenClassification

vita_audio/models/qwen2_mtp_v4_48_3/modular_qwen2.py:129

ClassQwen2MTPConfig

r""" This is the configuration class to store the configuration of a [`Qwen2Model`]. It is used to instantiate a Qwen2 model according to the

vita_audio/models/qwen2_mtp_v4_48_3/configuration_qwen2.py:25

next →1–100 of 121, ranked by callers