-
Notifications
You must be signed in to change notification settings - Fork 3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
控制生成音频的静音长度 #346
Comments
Hey @a122760, I'm here to help you with any bugs, questions, or contributions. Let's tackle this issue together! 在 OpenVoice 代码库中,控制生成音频静音长度的参数可以在 segments = get_vad_segments(
audio_vad,
output_sample=True,
min_speech_duration=0.1,
min_silence_duration=1,
method="silero",
) 这个参数决定了将一个片段视为单独音频片段所需的最小静音时长。通过调整 To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other |
No, this should control the silence duration during VAD segmentation, not the parameter for controlling the silence duration in TTS synthesized audio. Is there a way to control the silence duration in the synthesized audio? |
To control the silence duration in TTS synthesized audio in the OpenVoice codebase, you can modify the audio_segments += [0] * int((sr * 0.05)/speed) This line adds a silence of 0.05 seconds (or 50 milliseconds) between audio segments. You can adjust the silence duration by changing the value To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other |
如何控制生成音频的静音长度?有些音频的静音特别长,甚至占比50%,如何控制生成音频的静音长度呢?尤其是开头和结尾。
The text was updated successfully, but these errors were encountered: