Browse Source
Update readme
Signed-off-by: Jael Gu <mengjia.gu@zilliz.com>
main
1 changed files with
5 additions and
6 deletions
-
README.md
|
|
|
@ -9,23 +9,22 @@ This operator uses reads the waveform of an audio file and then applies VGGish t |
|
|
|
## Interface |
|
|
|
|
|
|
|
```python |
|
|
|
__call__(self, audio_path: str) |
|
|
|
__call__(self, datas: List[NamedTuple('data', [('audio', 'ndarray'), ('sample_rate', 'int')])]) |
|
|
|
``` |
|
|
|
|
|
|
|
**Args:** |
|
|
|
|
|
|
|
- audio_path: |
|
|
|
- the input audio path |
|
|
|
- supported types: str |
|
|
|
- datas: |
|
|
|
- a named tuple including audio data in numpy.ndarray and sample rate in integer |
|
|
|
|
|
|
|
**Returns:** |
|
|
|
|
|
|
|
The Operator returns a tuple Tuple[('embs', numpy.ndarray)] containing following fields: |
|
|
|
|
|
|
|
- embs: |
|
|
|
- vec: |
|
|
|
- embeddings of the audio |
|
|
|
- data type: `numpy.ndarray` |
|
|
|
- shape: (num_clips,128) |
|
|
|
- shape: (num_clips, 128) |
|
|
|
|
|
|
|
## Requirements |
|
|
|
|
|
|
|
|
