MCPcopy Create free account

hub / github.com/FunAudioLLM/Fun-Audio-Chat / functions

Functions257 in github.com/FunAudioLLM/Fun-Audio-Chat

⨍ Functions 257◇ Types & classes 28
↓ 1 callersFunctionmain
()
web_demo/server/server.py:1120
↓ 1 callersFunctionmultiple_function_checker
( func_descriptions: list, model_output: list, possible_answers: list, language: str, mode
evaluate/SpeechFCEval/utils/compute_metrics_bfcl.py:611
↓ 1 callersFunctionnormal_checker
( func_descriptions: list, model_output: list, possible_answers: dict, questio
evaluate/SpeechFCEval/utils/compute_metrics_acebench.py:486
↓ 1 callersFunctionoutput_record_table_v1
(record_list, table_file)
evaluate/SpeechFCEval/utils/compute_metrics_bfcl.py:819
↓ 1 callersFunctionoutput_record_table_v1
(record_list, table_file)
evaluate/SpeechFCEval/utils/compute_metrics_acebench.py:612
↓ 1 callersMethodpadded_and_mask_function
Pads a sequence of tensors to their maximum length on indicated `padding_side`. Then prepares a mask so that pad tokens are not atten
funaudiochat/modeling_funaudiochat.py:454
↓ 1 callersFunctionparallel_function_checker_no_order
( func_descriptions: list, model_output: list, possible_answers: list, language: str, mode
evaluate/SpeechFCEval/utils/compute_metrics_bfcl.py:542
↓ 1 callersFunctionparseEnv
()
web_demo/client/src/env.ts:6
↓ 1 callersFunctionparseInfo
(infos: any)
web_demo/client/src/pages/Conversation/hooks/useServerInfo.ts:30
↓ 1 callersFunctionparse_fun_audio_chat_function_v1
(text)
evaluate/SpeechFCEval/utils/compute_metrics_bfcl.py:787
↓ 1 callersFunctionparse_fun_audio_chat_function_v1
(text)
evaluate/SpeechFCEval/utils/compute_metrics_acebench.py:579
↓ 1 callersFunctionparse_json_function_call
(source_code)
evaluate/SpeechFCEval/utils/compute_metrics_bfcl.py:732
↓ 1 callersFunctionparse_json_line
(file_path)
evaluate/SpeechFCEval/utils/compute_metrics_bfcl.py:24
↓ 1 callersFunctionparse_json_line
(file_path)
evaluate/SpeechFCEval/utils/compute_metrics_acebench.py:23
↓ 1 callersFunctionpostRun
()
web_demo/client/public/assets/decoderWorker.min.js:547
↓ 1 callersFunctionpreRun
()
web_demo/client/public/assets/decoderWorker.min.js:533
↓ 1 callersMethodprepare_inputs_for_generation
( self, input_ids: torch.LongTensor, past_key_values: Optional[Cache] = None,
funaudiochat/modeling_funaudiochat.py:1170
↓ 1 callersFunctionreceiveInstance
(instance, module)
web_demo/client/public/assets/decoderWorker.min.js:667
↓ 1 callersFunctionregister_attention_plugin
Register FunAudioChat attention configuration plugin with LLaMA-Factory. This plugin handles FlashAttention-2 configuration for FunAudioChat
training/plugin/registration.py:51
↓ 1 callersFunctionregister_mm_plugins
Register FunAudioChat multimodal plugins with LLaMA-Factory.
training/plugin/registration.py:24
↓ 1 callersFunctionregister_templates
Register FunAudioChat chat templates with LLaMA-Factory.
training/plugin/registration.py:104
↓ 1 callersFunctionremoveRunDependency
(id)
web_demo/client/public/assets/decoderWorker.min.js:575
↓ 1 callersFunctionremove_generate_text_special_token
remove special tokens
web_demo/server/funaudiochat_infer.py:174
↓ 1 callersFunctionresolve_ast_by_type
(value)
evaluate/SpeechFCEval/utils/compute_metrics_bfcl.py:669
↓ 1 callersMethodsampling_step
(self, logits)
funaudiochat/modeling_funaudiochat.py:597
↓ 1 callersFunctionsave_json_line
(data_list, file_path)
evaluate/SpeechFCEval/utils/compute_metrics_bfcl.py:33
↓ 1 callersFunctionsave_json_line
(data_list, file_path)
evaluate/SpeechFCEval/utils/compute_metrics_acebench.py:32
↓ 1 callersMethodset_input_embeddings
(self, value: nn.Module)
funaudiochat/modeling_funaudiochat.py:287
↓ 1 callersFunctionshuffle
(array: number[])
web_demo/client/src/components/ImageGallery/ImageGallery.tsx:110
↓ 1 callersFunctionsimple_function_checker
( func_description: dict, model_output: dict, possible_answers: dict, question
evaluate/SpeechFCEval/utils/compute_metrics_acebench.py:338
↓ 1 callersMethodstartPlayback
()
web_demo/client/src/audio-processor.ts:114
↓ 1 callersFunctionstring_checker
(param: str, model_output: str, possible_answer: list)
evaluate/SpeechFCEval/utils/compute_metrics_bfcl.py:200
↓ 1 callersFunctionstring_checker
(param: str, model_output: str, possible_answer: list, function, question, test_category)
evaluate/SpeechFCEval/utils/compute_metrics_acebench.py:187
↓ 1 callersFunctiontokenizer
(audio_segment)
utils/cosyvoice_tokenizer.py:22
↓ 1 callersFunctiontools2function_v1
(tools)
evaluate/SpeechFCEval/utils/compute_metrics_bfcl.py:897
↓ 1 callersFunctiontools2function_v1
(tools)
evaluate/SpeechFCEval/utils/compute_metrics_acebench.py:690
↓ 1 callersFunctiontts_infer_streaming
(tts_model, tts_spk_embedding, tokens, offset, uuid, finalize=False, token_hop_len=5, pre_lookahead_len=3, dev
utils/cosyvoice_detokenizer.py:94
↓ 1 callersFunctiontype_checker
( param: str, value, possible_answer: list, expected_type_description: str, expected_type_
evaluate/SpeechFCEval/utils/compute_metrics_bfcl.py:108
↓ 1 callersFunctiontype_checker
( param: str, value, possible_answer: list, expected_type_description: str,
evaluate/SpeechFCEval/utils/compute_metrics_acebench.py:111
↓ 1 callersFunctionupdateGlobalBufferAndViews
(buf)
web_demo/client/public/assets/decoderWorker.min.js:512
↓ 1 callersFunctionuseServerAudio
({setGetAudioStats}: useServerAudioArgs)
web_demo/client/src/pages/Conversation/hooks/useServerAudio.ts:28
↓ 1 callersFunctionuseServerInfo
()
web_demo/client/src/pages/Conversation/hooks/useServerInfo.ts:63
↓ 1 callersFunctionuseServerText
()
web_demo/client/src/pages/Conversation/hooks/useServerText.ts:5
↓ 1 callersFunctionuseSocket
({ onMessage, uri, onDisconnect: onDisconnectProp, }: { onMessage?: (message: WSMessage) => void; ur
web_demo/client/src/pages/Conversation/hooks/useSocket.ts:5
↓ 1 callersFunctionuseUserAudio
({ constraints, onDataChunk, onRecordingStart = () => {}, onRecordingStop = () => {}, }: useUserAudioA
web_demo/client/src/pages/Conversation/hooks/useUserAudio.ts:23
↓ 1 callersFunctionvalidateAddUser
(response: unknown)
web_demo/client/src/pages/Queue/api/validators.ts:3
↓ 1 callersFunctionvalidateCheckUser
(response: unknown)
web_demo/client/src/pages/Queue/api/validators.ts:11
FunctionAudioVisualizer
({ analyser })
web_demo/client/src/pages/Conversation/components/AudioVisualizer/AudioVisualizer.tsx:7
FunctionButton
({ children, className, ...props })
web_demo/client/src/components/Button/Button.tsx:4
FunctionClientVisualizer
({ analyser, parent, copyCanvasRef })
web_demo/client/src/pages/Conversation/components/AudioVisualizer/ClientVisualizer.tsx:26
FunctionControls
()
web_demo/client/src/pages/Conversation/components/Controls/Controls.tsx:8
FunctionConversation
({ workerAddr, workerAuthId, audioContext, worklet, sessionAuthId, sessionId, onConversationEnd,
web_demo/client/src/pages/Conversation/Conversation.tsx:80
FunctionExitStatus
(status)
web_demo/client/public/assets/decoderWorker.min.js:855
FunctionImageGallery
(props: ImageGalleryProps)
web_demo/client/src/components/ImageGallery/ImageGallery.tsx:114
FunctionImageSelect
(props: ImageItemProps)
web_demo/client/src/components/ImageGallery/ImageGallery.tsx:76
FunctionInput
({className, error, ...props}:InputProps)
web_demo/client/src/components/Input/Input.tsx:5
FunctionModelParams
({ textTemperature, textTopk, audioTemperature, audioTopk, padMult, repetitionPenalty, repetitio
web_demo/client/src/pages/Conversation/components/ModelParams/ModelParams.tsx:10
FunctionQueue
()
web_demo/client/src/pages/Queue/Queue.tsx:19
FunctionServerAudio
({ setGetAudioStats, imageUrl, copyCanvasRef })
web_demo/client/src/pages/Conversation/components/ServerAudio/ServerAudio.tsx:10
FunctionServerAudioStats
({ getAudioStats }: ServerAudioStatsProps)
web_demo/client/src/pages/Conversation/components/ServerAudio/ServerAudioStats.tsx:16
FunctionServerInfo
()
web_demo/client/src/pages/Conversation/components/ServerInfo/ServerInfo.tsx:3
FunctionServerVisualizer
({ analyser, parent, imageUrl, copyCanvasRef })
web_demo/client/src/pages/Conversation/components/AudioVisualizer/ServerVisualizer.tsx:14
FunctionSwitchButton
({ children, className, ...props })
web_demo/client/src/components/Button/Button.tsx:16
FunctionTextDisplay
({ containerRef, displayColor })
web_demo/client/src/pages/Conversation/components/TextDisplay/TextDisplay.tsx:24
FunctionTextDisplayStats
({ totalTextMessages, })
web_demo/client/src/pages/Conversation/components/TextDisplay/TextDisplayStats.tsx:6
FunctionUserAudio
({ copyCanvasRef })
web_demo/client/src/pages/Conversation/components/UserAudio/UserAudio.tsx:9
FunctionUserAudioStats
({ sentMessagesCount, })
web_demo/client/src/pages/Conversation/components/UserAudio/UserAudioStats.tsx:7
Method__call__
Main method to prepare for the model one or several sequences(s) and audio(s). This method forwards the `text` and `kwargs` arguments
funaudiochat/processing_funaudiochat.py:129
Method__init__
( self, feature_extractor=None, speech_tokenizer=None, tokenizer=None,
funaudiochat/processing_funaudiochat.py:88
Method__init__
( self, num_mel_bins=128, encoder_layers=32, encoder_attention_heads=20,
funaudiochat/configuration_funaudiochat.py:103
Method__init__
( self, config: FunAudioChatAudioEncoderConfig, )
funaudiochat/modeling_funaudiochat.py:103
Method__init__
(self, config: FunAudioChatAudioEncoderConfig)
funaudiochat/modeling_funaudiochat.py:175
Method__init__
(self, length, channels, max_timescale=10000)
funaudiochat/modeling_funaudiochat.py:229
Method__init__
(self, config: FunAudioChatAudioEncoderConfig)
funaudiochat/modeling_funaudiochat.py:258
Method__init__
(self, config: FunAudioChatAudioEncoderConfig)
funaudiochat/modeling_funaudiochat.py:505
Method__init__
(self, config: FunAudioChatConfig)
funaudiochat/modeling_funaudiochat.py:772
Method__init__
(self, model_manager: GlobalModelManager, sample_rate: int = 24000, output_dir: str = "./output", tts_gpu: int
web_demo/server/server.py:199
Method__init__
(self, processor, skip_prompt=True, group_size=5, **decode_kwargs)
web_demo/server/funaudiochat_infer.py:32
Method__new__
(cls)
web_demo/server/server.py:157
Function_abort
()
web_demo/client/public/assets/decoderWorker.min.js:746
Function_emscripten_memcpy_big
(dest, src, num)
web_demo/client/public/assets/decoderWorker.min.js:749
Function_emscripten_resize_heap
(requestedSize)
web_demo/client/public/assets/decoderWorker.min.js:755
Function_fd_close
(fd)
web_demo/client/public/assets/decoderWorker.min.js:786
Function_fd_seek
(fd, offset_low, offset_high, whence, newOffset)
web_demo/client/public/assets/decoderWorker.min.js:789
Function_fd_write
(fd, iov, iovcnt, pnum)
web_demo/client/public/assets/decoderWorker.min.js:790
Method_freeze_parameters
(self)
funaudiochat/modeling_funaudiochat.py:279
Method_get_arguments_from_pretrained
Identify and instantiate the subcomponents of Processor classes, like image processors and tokenizers. This method uses the Processor
funaudiochat/processing_funaudiochat.py:311
Method_get_feat_extract_output_lengths
Computes the output length of the convolutional layers and the output length of the audio encoder
funaudiochat/modeling_funaudiochat.py:554
Method_init_weights
(self, module)
funaudiochat/modeling_funaudiochat.py:57
Method_sample
r""" Generates sequences of token ids for models with a language modeling head using **multinomial sampling** and can be used for text
funaudiochat/modeling_funaudiochat.py:1218
Methodaccumulate_pcm_loop
()
web_demo/server/server.py:728
Functionast_parse
( input_str: str, language: str, has_tool_call_tag: bool = False, )
evaluate/SpeechFCEval/utils/compute_metrics_bfcl.py:751
Methodbatch_decode
This method forwards all its arguments to FunAudioChatTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docs
funaudiochat/processing_funaudiochat.py:296
Functionconfigure_attn_implementation
Configure attention implementation for FunAudioChat model. Args: config: The model configuration model_args: Model argum
training/plugin/attention.py:34
Functionconfigure_attn_implementation_wrapper
(config, model_args)
training/plugin/registration.py:70
Methodconstructor
()
web_demo/client/src/audio-processor.ts:21
Methodconstructor
(message:string)
web_demo/client/src/pages/Queue/api/errors/response_error.ts:2
Methodconstructor
(message:string, status:number)
web_demo/client/src/pages/Queue/api/errors/api_error.ts:4
Functionconvert_format
(example, rank, audio_dir, delay_token_nums=10)
training/process/data_process.py:29
Methodcrq_generate_forward
( self, inputs_embeds=None, audio_embeds=None, labels=None, attention_
funaudiochat/modeling_funaudiochat.py:615
← previousnext →101–200 of 257, ranked by callers