File size: 3,313 Bytes
c72e80d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 |
import torch
class VADIterator:
def __init__(
self,
model,
threshold: float = 0.5,
sampling_rate: int = 16000,
min_silence_duration_ms: int = 100,
speech_pad_ms: int = 30,
):
"""
Mainly taken from https://github.com/snakers4/silero-vad
Class for stream imitation
Parameters
----------
model: preloaded .jit/.onnx 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_silence_duration_ms: int (default - 100 milliseconds)
In the end of each speech chunk wait for min_silence_duration_ms before separating it
speech_pad_ms: int (default - 30 milliseconds)
Final speech chunks are padded by speech_pad_ms each side
"""
self.model = model
self.threshold = threshold
self.sampling_rate = sampling_rate
self.is_speaking = False
self.buffer = []
if sampling_rate not in [8000, 16000]:
raise ValueError(
"VADIterator does not support sampling rates other than [8000, 16000]"
)
self.min_silence_samples = sampling_rate * min_silence_duration_ms / 1000
self.speech_pad_samples = sampling_rate * speech_pad_ms / 1000
self.reset_states()
def reset_states(self):
self.model.reset_states()
self.triggered = False
self.temp_end = 0
self.current_sample = 0
@torch.no_grad()
def __call__(self, x):
"""
x: torch.Tensor
audio chunk (see examples in repo)
return_seconds: bool (default - False)
whether return timestamps in seconds (default - samples)
"""
if not torch.is_tensor(x):
try:
x = torch.Tensor(x)
except Exception:
raise TypeError("Audio cannot be casted to tensor. Cast it manually")
window_size_samples = len(x[0]) if x.dim() == 2 else len(x)
self.current_sample += window_size_samples
speech_prob = self.model(x, self.sampling_rate).item()
if (speech_prob >= self.threshold) and self.temp_end:
self.temp_end = 0
if (speech_prob >= self.threshold) and not self.triggered:
self.triggered = True
return None
if (speech_prob < self.threshold - 0.15) and self.triggered:
if not self.temp_end:
self.temp_end = self.current_sample
if self.current_sample - self.temp_end < self.min_silence_samples:
return None
else:
# end of speak
self.temp_end = 0
self.triggered = False
spoken_utterance = self.buffer
self.buffer = []
return spoken_utterance
if self.triggered:
self.buffer.append(x)
return None
|