|
|
|
@ -18,48 +18,22 @@ As suggested, it is suitable to extract features at high level or warm up a larg |
|
|
|
|
|
|
|
Generate embeddings for the audio "test.wav". |
|
|
|
|
|
|
|
*Write the pipeline in simplified style*: |
|
|
|
*Write a same pipeline with explicit inputs/outputs name specifications:* |
|
|
|
|
|
|
|
```python |
|
|
|
import towhee |
|
|
|
|
|
|
|
( |
|
|
|
towhee.glob('test.wav') |
|
|
|
.audio_decode.ffmpeg() |
|
|
|
.runas_op(func=lambda x:[y[0] for y in x]) |
|
|
|
.audio_embedding.vggish() |
|
|
|
.show() |
|
|
|
from towhee import pipe, ops |
|
|
|
|
|
|
|
p = ( |
|
|
|
pipe.input('path') |
|
|
|
.map('path', 'frame', ops.audio_decode.ffmpeg()) |
|
|
|
.map('frame', 'vecs', ops.audio_embedding.vggish()) |
|
|
|
.output('vecs') |
|
|
|
) |
|
|
|
|
|
|
|
p('test.wav').get()[0] |
|
|
|
``` |
|
|
|
| [-0.4931737, -0.40068552, -0.032327592, ...] shape=(10, 128) | |
|
|
|
|
|
|
|
*Write a same pipeline with explicit inputs/outputs name specifications:* |
|
|
|
|
|
|
|
```python |
|
|
|
import towhee |
|
|
|
|
|
|
|
( |
|
|
|
towhee.glob['path']('test.wav') |
|
|
|
.audio_decode.ffmpeg['path', 'frames']() |
|
|
|
.runas_op['frames', 'frames'](func=lambda x:[y[0] for y in x]) |
|
|
|
.audio_embedding.vggish['frames', 'vecs']() |
|
|
|
.select['path', 'vecs']() |
|
|
|
.show() |
|
|
|
) |
|
|
|
``` |
|
|
|
[array([[-0.4931737 , -0.40068552, -0.03232759, ..., -0.33428153, |
|
|
|
0.1333081 , -0.25221825], |
|
|
|
[-0.49023268, -0.40161428, -0.03255743, ..., -0.33395663, |
|
|
|
0.13261834, -0.25324696], |
|
|
|
[-0.4992406 , -0.39848825, -0.03186834, ..., -0.33684137, |
|
|
|
0.13326398, -0.25385314], |
|
|
|
..., |
|
|
|
[-0.49047503, -0.40119144, -0.03144619, ..., -0.33282205, |
|
|
|
0.13334712, -0.2520305 ], |
|
|
|
[-0.48861542, -0.40097567, -0.03173053, ..., -0.33255234, |
|
|
|
0.13278192, -0.25157905], |
|
|
|
[-0.4886143 , -0.40098593, -0.03175077, ..., -0.3325425 , |
|
|
|
0.13271847, -0.25159872]], dtype=float32)] |
|
|
|
|
|
|
|
<br /> |
|
|
|
|
|
|
|
|
