You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Performs audio transcription using OpenVino GenAI Whisper model. for more details on the whisper ASR check out [OpenVino GenAI Documentation](https://docs.openvino.ai/2025/api/genai_api/_autosummary/openvino_genai.WhisperPipeline.html#openvino_genai.WhisperPipeline)
4
+
5
+
6
+
```sh
7
+
Element Flags:
8
+
9
+
Pad Templates:
10
+
SINK template: 'sink'
11
+
Availability: Always
12
+
Capabilities:
13
+
audio/x-raw
14
+
format: S16LE
15
+
rate: 16000
16
+
channels: 1
17
+
18
+
SRC template: 'src'
19
+
Availability: Always
20
+
Capabilities:
21
+
audio/x-raw
22
+
format: S16LE
23
+
rate: 16000
24
+
channels: 1
25
+
26
+
Element has no clocking capabilities.
27
+
Element has no URI handling capabilities.
28
+
29
+
Pads:
30
+
SINK: 'sink'
31
+
Pad Template: 'sink'
32
+
SRC: 'src'
33
+
Pad Template: 'src'
34
+
35
+
Element Properties:
36
+
37
+
device : Device to use for inference (CPU, GPU)
38
+
flags: readable, writable
39
+
String. Default: "CPU"
40
+
41
+
model : Path to the model directory
42
+
flags: readable, writable
43
+
String. Default: null
44
+
45
+
model-type : model_type value to use whisper for inference: 'whisper' (supported).
0 commit comments