Advanced Configuration
Track Constraints
You can specify the track_constraints
parameter to control how the data is streamed to the server. The full documentation on track constraints is here.
For example, you can control the size of the frames captured from the webcam like so:
track_constraints = {
"width": {"ideal": 500},
"height": {"ideal": 500},
"frameRate": {"ideal": 30},
}
webrtc = WebRTC(track_constraints=track_constraints,
modality="video",
mode="send-receive")
The RTC Configuration
You can configure how the connection is created on the client by passing an rtc_configuration
parameter to the WebRTC
component constructor.
See the list of available arguments here.
When deploying on a remote server, an rtc_configuration
parameter must be passed in. See Deployment.
Reply on Pause Voice-Activity-Detection
The ReplyOnPause
class runs a Voice Activity Detection (VAD) algorithm to determine when a user has stopped speaking.
- First, the algorithm determines when the user has started speaking.
- Then it groups the audio into chunks.
- On each chunk, we determine the length of human speech in the chunk.
- If the length of human speech is below a threshold, a pause is detected.
The following parameters control this argument:
from gradio_webrtc import AlgoOptions, ReplyOnPause, WebRTC
options = AlgoOptions(audio_chunk_duration=0.6, # (1)
started_talking_threshold=0.2, # (2)
speech_threshold=0.1, # (3)
)
with gr.Blocks as demo:
audio = WebRTC(...)
audio.stream(ReplyOnPause(..., algo_options=algo_options)
)
demo.launch()
- This is the length (in seconds) of audio chunks.
- If the chunk has more than 0.2 seconds of speech, the user started talking.
- If, after the user started speaking, there is a chunk with less than 0.1 seconds of speech, the user stopped speaking.
Stream Handler Output Audio
You can configure the output audio chunk size of ReplyOnPause
(and any StreamHandler
)
with the output_sample_rate
and output_frame_size
parameters.
The following code (which uses the default values of these parameters), states that each output chunk will be a frame of 960 samples at a frame rate of 24,000
hz. So it will correspond to 0.04
seconds.