fumiama/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI.git synced 2026-06-07 19:40:44 +08:00
Code Activity

optimize: some training optimizations (#95)

Browse Source 
* optimzie(train&uvr5): rm sf & simp. AudioPre

* fix(audio): too many mallocs

* feat(audio): load_audio support stereo

* fix(audio): float32 wav saving

* fix(train): missing ckpt var
This commit is contained in:
源文雨
2024-11-28 03:20:14 +09:00
committed by GitHub
parent f4644ec1ec
commit a8783c6639
19 changed files with 163 additions and 433 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tools/cmd/onnx/infer.py
View File

@@ -1,8 +1,9 @@
import soundfile
import librosa
from rvc.onnx import RVC
from infer.lib.audio import save_audio
hop_size = 512
sampling_rate = 40000 # 采样率
f0_up_key = 0 # 升降调
@@ -19,4 +20,4 @@ wav, sr = librosa.load(wav_path, sr=sampling_rate)
audio = model.infer(wav, sr, sampling_rate, sid, f0_method, f0_up_key)
soundfile.write(out_path, audio, sampling_rate)
save_audio(out_path, audio, sampling_rate)