Spaces:
Running
Running
File size: 4,978 Bytes
3749184 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 |
import onnxruntime
import librosa
import numpy as np
import soundfile
class ContentVec:
def __init__(self, vec_path="pretrained/vec-768-layer-12.onnx", device=None):
print("load model(s) from {}".format(vec_path))
if device == "cpu" or device is None:
providers = ["CPUExecutionProvider"]
elif device == "cuda":
providers = ["CUDAExecutionProvider", "CPUExecutionProvider"]
else:
raise RuntimeError("Unsportted Device")
self.model = onnxruntime.InferenceSession(vec_path, providers=providers)
def __call__(self, wav):
return self.forward(wav)
def forward(self, wav):
feats = wav
if feats.ndim == 2: # double channels
feats = feats.mean(-1)
assert feats.ndim == 1, feats.ndim
feats = np.expand_dims(np.expand_dims(feats, 0), 0)
onnx_input = {self.model.get_inputs()[0].name: feats}
logits = self.model.run(None, onnx_input)[0]
return logits.transpose(0, 2, 1)
def get_f0_predictor(f0_predictor, hop_length, sampling_rate, **kargs):
if f0_predictor == "pm":
from infer_pack.modules.F0Predictor.PMF0Predictor import PMF0Predictor
f0_predictor_object = PMF0Predictor(
hop_length=hop_length, sampling_rate=sampling_rate
)
elif f0_predictor == "harvest":
from infer_pack.modules.F0Predictor.HarvestF0Predictor import HarvestF0Predictor
f0_predictor_object = HarvestF0Predictor(
hop_length=hop_length, sampling_rate=sampling_rate
)
elif f0_predictor == "dio":
from infer_pack.modules.F0Predictor.DioF0Predictor import DioF0Predictor
f0_predictor_object = DioF0Predictor(
hop_length=hop_length, sampling_rate=sampling_rate
)
else:
raise Exception("Unknown f0 predictor")
return f0_predictor_object
class OnnxRVC:
def __init__(
self,
model_path,
sr=40000,
hop_size=512,
vec_path="vec-768-layer-12",
device="cpu",
):
vec_path = f"pretrained/{vec_path}.onnx"
self.vec_model = ContentVec(vec_path, device)
if device == "cpu" or device is None:
providers = ["CPUExecutionProvider"]
elif device == "cuda":
providers = ["CUDAExecutionProvider", "CPUExecutionProvider"]
else:
raise RuntimeError("Unsportted Device")
self.model = onnxruntime.InferenceSession(model_path, providers=providers)
self.sampling_rate = sr
self.hop_size = hop_size
def forward(self, hubert, hubert_length, pitch, pitchf, ds, rnd):
onnx_input = {
self.model.get_inputs()[0].name: hubert,
self.model.get_inputs()[1].name: hubert_length,
self.model.get_inputs()[2].name: pitch,
self.model.get_inputs()[3].name: pitchf,
self.model.get_inputs()[4].name: ds,
self.model.get_inputs()[5].name: rnd,
}
return (self.model.run(None, onnx_input)[0] * 32767).astype(np.int16)
def inference(
self,
raw_path,
sid,
f0_method="dio",
f0_up_key=0,
pad_time=0.5,
cr_threshold=0.02,
):
f0_min = 50
f0_max = 1100
f0_mel_min = 1127 * np.log(1 + f0_min / 700)
f0_mel_max = 1127 * np.log(1 + f0_max / 700)
f0_predictor = get_f0_predictor(
f0_method,
hop_length=self.hop_size,
sampling_rate=self.sampling_rate,
threshold=cr_threshold,
)
wav, sr = librosa.load(raw_path, sr=self.sampling_rate)
org_length = len(wav)
if org_length / sr > 50.0:
raise RuntimeError("Reached Max Length")
wav16k = librosa.resample(wav, orig_sr=self.sampling_rate, target_sr=16000)
wav16k = wav16k
hubert = self.vec_model(wav16k)
hubert = np.repeat(hubert, 2, axis=2).transpose(0, 2, 1).astype(np.float32)
hubert_length = hubert.shape[1]
pitchf = f0_predictor.compute_f0(wav, hubert_length)
pitchf = pitchf * 2 ** (f0_up_key / 12)
pitch = pitchf.copy()
f0_mel = 1127 * np.log(1 + pitch / 700)
f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - f0_mel_min) * 254 / (
f0_mel_max - f0_mel_min
) + 1
f0_mel[f0_mel <= 1] = 1
f0_mel[f0_mel > 255] = 255
pitch = np.rint(f0_mel).astype(np.int64)
pitchf = pitchf.reshape(1, len(pitchf)).astype(np.float32)
pitch = pitch.reshape(1, len(pitch))
ds = np.array([sid]).astype(np.int64)
rnd = np.random.randn(1, 192, hubert_length).astype(np.float32)
hubert_length = np.array([hubert_length]).astype(np.int64)
out_wav = self.forward(hubert, hubert_length, pitch, pitchf, ds, rnd).squeeze()
out_wav = np.pad(out_wav, (0, 2 * self.hop_size), "constant")
return out_wav[0:org_length]
|