|
|
@ -43,7 +43,8 @@ import towhee |
|
|
towhee.glob['path']('test.wav') |
|
|
towhee.glob['path']('test.wav') |
|
|
.audio_decode.ffmpeg['path', 'frames']() |
|
|
.audio_decode.ffmpeg['path', 'frames']() |
|
|
.runas_op['frames', 'frames'](func=lambda x:[y[0] for y in x]) |
|
|
.runas_op['frames', 'frames'](func=lambda x:[y[0] for y in x]) |
|
|
.audio_embedding.data2vec['frames', 'vecs'](model_name="facebook/data2vec-audio-base-960h") |
|
|
|
|
|
|
|
|
.audio_embedding.data2vec['frames', 'vecs'](model_name="facebook/data2vec-audio-base-960h") |
|
|
|
|
|
.select['path', 'vecs']() |
|
|
.show() |
|
|
.show() |
|
|
) |
|
|
) |
|
|
``` |
|
|
``` |
|
|
@ -68,7 +69,7 @@ The model name in string. |
|
|
The default value is "facebook/data2vec-audio-base-960h". |
|
|
The default value is "facebook/data2vec-audio-base-960h". |
|
|
|
|
|
|
|
|
Supported model name: |
|
|
Supported model name: |
|
|
- |
|
|
|
|
|
|
|
|
- |
|
|
- facebook/data2vec-audio-base-960h |
|
|
- facebook/data2vec-audio-base-960h |
|
|
- facebook/data2vec-audio-large-960h |
|
|
- facebook/data2vec-audio-large-960h |
|
|
- facebook/data2vec-audio-base |
|
|
- facebook/data2vec-audio-base |
|
|
@ -96,6 +97,3 @@ An audio embedding operator generates vectors in numpy.ndarray given an audio fi |
|
|
**Returns:** *numpy.ndarray* |
|
|
**Returns:** *numpy.ndarray* |
|
|
|
|
|
|
|
|
The audio embedding extracted by model. |
|
|
The audio embedding extracted by model. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
