File size: 2,879 Bytes
7316673 8c51444 7316673 8c51444 |
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 99 100 101 102 |
import os
import torch
from rvc.lib.predictors.RMVPE import RMVPE0Predictor
from torchfcpe import spawn_bundled_infer_model
import torchcrepe
# ✅ Import DJCM
from djcm import DJCMExtractor
class RMVPE:
def __init__(self, device, model_name="rmvpe.pt", sample_rate=16000, hop_size=160):
self.device = device
self.sample_rate = sample_rate
self.hop_size = hop_size
self.model = RMVPE0Predictor(
os.path.join("rvc", "models", "predictors", model_name),
device=self.device,
)
def get_f0(self, x, filter_radius=0.03):
f0 = self.model.infer_from_audio(x, thred=filter_radius)
return f0
class CREPE:
def __init__(self, device, sample_rate=16000, hop_size=160):
self.device = device
self.sample_rate = sample_rate
self.hop_size = hop_size
def get_f0(self, x, f0_min=50, f0_max=1100, p_len=None, model="full"):
if p_len is None:
p_len = x.shape[0] // self.hop_size
if not torch.is_tensor(x):
x = torch.from_numpy(x)
batch_size = 512
f0, pd = torchcrepe.predict(
x.float().to(self.device).unsqueeze(dim=0),
self.sample_rate,
self.hop_size,
f0_min,
f0_max,
model=model,
batch_size=batch_size,
device=self.device,
return_periodicity=True,
)
pd = torchcrepe.filter.median(pd, 3)
f0 = torchcrepe.filter.mean(f0, 3)
f0[pd < 0.1] = 0
f0 = f0[0].cpu().numpy()
return f0
class FCPE:
def __init__(self, device, sample_rate=16000, hop_size=160):
self.device = device
self.sample_rate = sample_rate
self.hop_size = hop_size
self.model = spawn_bundled_infer_model(self.device)
def get_f0(self, x, p_len=None, filter_radius=0.006):
if p_len is None:
p_len = x.shape[0] // self.hop_size
if not torch.is_tensor(x):
x = torch.from_numpy(x)
f0 = (
self.model.infer(
x.float().to(self.device).unsqueeze(0),
sr=self.sample_rate,
decoder_mode="local_argmax",
threshold=filter_radius,
)
.squeeze()
.cpu()
.numpy()
)
return f0
class DJCM:
def __init__(self, device, model_name="djcm.pt", sample_rate=16000, hop_size=160):
self.device = device
self.sample_rate = sample_rate
self.hop_size = hop_size
self.model = DJCMExtractor(os.path.join("weights", model_name), device=self.device)
def get_f0(self, x, p_len=None):
if not torch.is_tensor(x):
x = torch.from_numpy(x).cpu().numpy() # pastikan ke numpy
f0 = self.model(x, sr=self.sample_rate)
return f0
|