Change the default merge window to 5.
Browse filesThis is effectively 7 seconds, as each speech section is
also padded with one second.
app.py
CHANGED
@@ -197,7 +197,7 @@ def createUi(inputAudioMaxDuration, share=False, server_name: str = None):
|
|
197 |
gr.Audio(source="microphone", type="filepath", label="Microphone Input"),
|
198 |
gr.Dropdown(choices=["transcribe", "translate"], label="Task"),
|
199 |
gr.Dropdown(choices=["none", "silero-vad", "silero-vad-skip-gaps", "periodic-vad"], label="VAD"),
|
200 |
-
gr.Number(label="VAD - Merge Window (s)", precision=0, value=
|
201 |
gr.Number(label="VAD - Max Merge Size (s)", precision=0, value=150)
|
202 |
], outputs=[
|
203 |
gr.File(label="Download"),
|
|
|
197 |
gr.Audio(source="microphone", type="filepath", label="Microphone Input"),
|
198 |
gr.Dropdown(choices=["transcribe", "translate"], label="Task"),
|
199 |
gr.Dropdown(choices=["none", "silero-vad", "silero-vad-skip-gaps", "periodic-vad"], label="VAD"),
|
200 |
+
gr.Number(label="VAD - Merge Window (s)", precision=0, value=5),
|
201 |
gr.Number(label="VAD - Max Merge Size (s)", precision=0, value=150)
|
202 |
], outputs=[
|
203 |
gr.File(label="Download"),
|