input and output

[JJun-Guo]

Hi,I input a speech sample with 44.1kHz sample rate and 16 (Sampling depth)，the output is a speech with 16kHZ sample rate and 32 (Sampling depth), how can I get the default sampling depth speech sample???

[snakers4]

Hi,

The VAD accepts only 16 kHz or 8 kHz.

silero-vad/utils_vad.py

Lines 119 to 171 in 7c671a7

	def get_speech_timestamps(audio: torch.Tensor,
	model,
	threshold: float = 0.5,
	sampling_rate: int = 16000,
	min_speech_duration_ms: int = 250,
	min_silence_duration_ms: int = 100,
	window_size_samples: int = 1536,
	speech_pad_ms: int = 30,
	return_seconds: bool = False,
	visualize_probs: bool = False):
	"""
	This method is used for splitting long audios into speech chunks using silero VAD
	Parameters
	----------
	audio: torch.Tensor, one dimensional
	One dimensional float torch.Tensor, other types are casted to torch if possible
	model: preloaded .jit silero VAD model
	threshold: float (default - 0.5)
	Speech threshold. Silero VAD outputs speech probabilities for each audio chunk, probabilities ABOVE this value are considered as SPEECH.
	It is better to tune this parameter for each dataset separately, but "lazy" 0.5 is pretty good for most datasets.
	sampling_rate: int (default - 16000)
	Currently silero VAD models support 8000 and 16000 sample rates
	min_speech_duration_ms: int (default - 250 milliseconds)
	Final speech chunks shorter min_speech_duration_ms are thrown out
	min_silence_duration_ms: int (default - 100 milliseconds)
	In the end of each speech chunk wait for min_silence_duration_ms before separating it
	window_size_samples: int (default - 1536 samples)
	Audio chunks of window_size_samples size are fed to the silero VAD model.
	WARNING! Silero VAD models were trained using 512, 1024, 1536 samples for 16000 sample rate and 256, 512, 768 samples for 8000 sample rate.
	Values other than these may affect model perfomance!!
	speech_pad_ms: int (default - 30 milliseconds)
	Final speech chunks are padded by speech_pad_ms each side
	return_seconds: bool (default - False)
	whether return timestamps in seconds (default - samples)
	visualize_probs: bool (default - False)
	whether draw prob hist or not
	Returns
	----------
	speeches: list of dicts
	list containing ends and beginnings of speech chunks (samples or seconds based on return_seconds)
	"""

[JJun-Guo]

yes, the speech with other sample rate will be resampled with 16kHz? and the sampling depth can be choosed

[snakers4]

You need to resample.

[JJun-Guo]

I get the following code including the resample process, do i need to resample the speech manually？
def read_audio(path: str,
sampling_rate: int = 16000):
wav, sr = torchaudio.load(path)

if wav.size(0) > 1:
    wav = wav.mean(dim=0, keepdim=True)

if sr != sampling_rate:
    transform = torchaudio.transforms.Resample(orig_freq=sr,
                                               new_freq=sampling_rate)
    wav = transform(wav)
    sr = sampling_rate
assert sr == sampling_rate
return wav.squeeze(0)

[snakers4]

do i need to resample the speech manually

You need to make sure that incoming samples are either 16 kHz or 8 kHz