Browse Source
Update README
Signed-off-by: Jael Gu <mengjia.gu@zilliz.com>
main
1 changed files with
2 additions and
2 deletions
-
README.md
|
|
@ -11,7 +11,7 @@ Each vector represents for an audio clip with a fixed length of around 1s. |
|
|
This operator generates audio embeddings with fingerprinting method introduced by [Neural Audio Fingerprint](https://arxiv.org/abs/2010.11910). |
|
|
This operator generates audio embeddings with fingerprinting method introduced by [Neural Audio Fingerprint](https://arxiv.org/abs/2010.11910). |
|
|
The model is implemented in Pytorch. |
|
|
The model is implemented in Pytorch. |
|
|
We've also trained the nnfp model with [FMA dataset](https://github.com/mdeff/fma) (& some noise audio) and shared weights in this operator. |
|
|
We've also trained the nnfp model with [FMA dataset](https://github.com/mdeff/fma) (& some noise audio) and shared weights in this operator. |
|
|
The nnfp operator is suitable to generate audio fingerprints. |
|
|
|
|
|
|
|
|
The nnfp operator is suitable for audio fingerprinting. |
|
|
|
|
|
|
|
|
<br /> |
|
|
<br /> |
|
|
|
|
|
|
|
|
@ -84,7 +84,7 @@ An audio embedding operator generates vectors in numpy.ndarray given towhee audi |
|
|
*data: List[towhee.types.audio_frame.AudioFrame]* |
|
|
*data: List[towhee.types.audio_frame.AudioFrame]* |
|
|
|
|
|
|
|
|
Input audio data is a list of towhee audio frames. |
|
|
Input audio data is a list of towhee audio frames. |
|
|
The input data should represent for an audio longer than 1s. |
|
|
|
|
|
|
|
|
The audio input should be at least 1s. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
**Returns**: |
|
|
**Returns**: |
|
|
|
