data_juicer.ops.mapper.video_audio_speech_emotion_mapper module#

class data_juicer.ops.mapper.video_audio_speech_emotion_mapper.VideoAudioSpeechEmotionMapper(*args, **kwargs)[源代码]#

基类：Mapper

Mapper to generate video tags from audio streams extracted by video using the Audio Spectrogram Transformer.

Source: This operator is a part of HumanVBench (CVPR 2026).

__init__(model_dir_emo='FunAudioLLM/SenseVoiceSmall', speech_Emo: str = 'speech_emotion', *args, **kwargs)[源代码]#

Initialization method.

参数:

  • args -- extra args

  • kwargs -- extra args

process_single(sample, rank=None)[源代码]#

For sample level, sample --> sample

参数:

sample -- sample to process

返回:

processed sample