Microphone Demo for Rhino Speech-to-Intent engine. It creates an input audio stream from a microphone, monitors
it, and extracts the intent from the speech command. It optionally saves the recorded audio into a file for further
debugging.
Definition at line 21 of file rhino_demo_mic.py.
def rhino_demo_mic.RhinoDemo.__init__ |
( |
|
self, |
|
|
|
access_key, |
|
|
|
library_path, |
|
|
|
model_path, |
|
|
|
context_path, |
|
|
|
require_endpoint, |
|
|
|
audio_device_index = None , |
|
|
|
output_path = None |
|
) |
| |
Constructor.
:param access_key: AccessKey obtained from Picovoice Console (https://console.picovoice.ai/).
:param library_path: Absolute path to Rhino's dynamic library.
:param model_path: Absolute path to file containing model parameters.
:param context_path: Absolute path to file containing context model (file with `.rhn` extension). A context
represents the set of expressions (spoken commands), intents, and intent arguments (slots) within a domain of
interest.
:param require_endpoint If set to `False`, Rhino does not require an endpoint (chunk of silence) before
finishing inference.
:param audio_device_index: Optional argument. If provided, audio is recorded from this input device. Otherwise,
the default audio input device is used.
:param output_path: If provided recorded audio will be stored in this location at the end of the run.
Definition at line 28 of file rhino_demo_mic.py.