video_audio_ASR_mapper#
Perform automatic speech recognition (ASR) on video audio streams using the SenseVoiceSmall model. This operator extracts audio from videos and transcribes speech content. It must be operated after video_tagging_from_audio_mapper, as it only processes videos tagged as containing speech.
使用 SenseVoiceSmall 模型对视频音频流进行自动语音识别（ASR）。此算子从视频中提取音频并转录语音内容。它必须在 video_tagging_from_audio_mapper 之后运行，因为仅处理被标记为包含语音的视频。
Type 算子类型: mapper
Tags 标签: gpu, hf, video
🔧 Parameter Configuration 参数配置#
name 参数名 |
type 类型 |
default 默认值 |
desc 说明 |
|---|---|---|---|
|
<class 'str'> |
|
path to the SenseVoiceSmall ASR model. |
|
<class 'str'> |
|
field name to store the ASR results. |
|
|
extra args |
|
|
|
extra args |