pony123/ChatGLM2-Voice-Cloning

1 2## Mel-filterbank3mel_window_length = 25  # In milliseconds4mel_window_step = 10    # In milliseconds5mel_n_channels = 406 7 8## Audio9sampling_rate = 1600010# Number of spectrogram frames in a partial utterance11partials_n_frames = 160     # 1600 ms12# Number of spectrogram frames at inference13inference_n_frames = 80     #  800 ms14 15 16## Voice Activation Detection17# Window size of the VAD. Must be either 10, 20 or 30 milliseconds.18# This sets the granularity of the VAD. Should not need to be changed.19vad_window_length = 30  # In milliseconds20# Number of frames to average together when performing the moving average smoothing.21# The larger this value, the larger the VAD variations must be to not get smoothed out. 22vad_moving_average_width = 823# Maximum number of consecutive silent frames a segment can have.24vad_max_silence_length = 625 26 27## Audio volume normalization28audio_norm_target_dBFS = -3029 30