1berry/wokada-voice-changer
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

WIP: support DDSP_SVC

Browse Source
This commit is contained in:
wataru 2023-03-24 16:19:01 +09:00
parent 807120201f
commit 8a4e76795a
2 changed files with 3 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
server/voice_changer/DDSP_SVC/DDSP_SVC.py
View File

@ -24,7 +24,7 @@ from slicer import Slicer
import librosa import librosa
providers = ['OpenVINOExecutionProvider', "CUDAExecutionProvider", "DmlExecutionProvider", "CPUExecutionProvider"] providers = ['OpenVINOExecutionProvider', "CUDAExecutionProvider", "DmlExecutionProvider", "CPUExecutionProvider"]
import resampy
from scipy.io import wavfile from scipy.io import wavfile
SAMPLING_RATE = 44100 SAMPLING_RATE = 44100
@ -234,7 +234,7 @@ class DDSP_SVC:
return np.zeros(convertSize).astype(np.int16) return np.zeros(convertSize).astype(np.int16)
with torch.no_grad(): with torch.no_grad():
spk_id = torch.LongTensor(np.array([[int(2)]])) spk_id = torch.LongTensor(np.array([[int(1)]]))
seg_output, _, (s_h, s_n) = self.model(c, f0, volume, spk_id=spk_id, spk_mix_dict=None) seg_output, _, (s_h, s_n) = self.model(c, f0, volume, spk_id=spk_id, spk_mix_dict=None)
seg_output *= mask seg_output *= mask
@ -245,7 +245,6 @@ class DDSP_SVC:
self.args.data.block_size, self.args.data.block_size,
adaptive_key=float(0)) adaptive_key=float(0))
result = seg_output.squeeze().cpu().numpy() * 32768.0 result = seg_output.squeeze().cpu().numpy() * 32768.0
return np.array(result).astype(np.int16) return np.array(result).astype(np.int16)
def inference(self, data): def inference(self, data):

4
server/voice_changer/VoiceChanger.py
View File

@ -244,12 +244,10 @@ class VoiceChanger():
self.ioRecorder.writeOutput(outputData.tobytes()) self.ioRecorder.writeOutput(outputData.tobytes())
# if receivedData.shape[0] != outputData.shape[0]: # if receivedData.shape[0] != outputData.shape[0]:
# print(f"Padding, in:{receivedData.shape[0]} out:{outputData.shape[0]}")
# outputData = pad_array(outputData, receivedData.shape[0]) # outputData = pad_array(outputData, receivedData.shape[0])
# # print_convert_processing( # # print_convert_processing(
# # f" Padded!, Output data size of {result.shape[0]}/{processing_sampling_rate}hz {outputData.shape[0]}/{self.settings.inputSampleRate}hz") # # f" Padded!, Output data size of {result.shape[0]}/{processing_sampling_rate}hz {outputData.shape[0]}/{self.settings.inputSampleRate}hz")
# print(
# f" Padded!, Output data size of {result.shape[0]}/{processing_sampling_rate}hz {outputData.shape[0]}/{self.settings.inputSampleRate}hz")
postprocess_time = t.secs postprocess_time = t.secs
print_convert_processing(f" [fin] Input/Output size:{receivedData.shape[0]},{outputData.shape[0]}") print_convert_processing(f" [fin] Input/Output size:{receivedData.shape[0]},{outputData.shape[0]}")