OPENGIT/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2025-02-06 21:52:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

load audio with gradio-file

Browse Source
This commit is contained in:
Ftps 2023-08-27 19:14:01 +09:00
parent 5251e75ab1
commit 3f3177b5ce
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
infer/lib/audio.py
View File

@ -1,3 +1,4 @@
import librosa
import ffmpeg import ffmpeg
import numpy as np import numpy as np
@ -15,7 +16,13 @@ def load_audio(file, sr):
.output("-", format="f32le", acodec="pcm_f32le", ac=1, ar=sr) .output("-", format="f32le", acodec="pcm_f32le", ac=1, ar=sr)
.run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True) .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
) )
return np.frombuffer(out, np.float32).flatten()
except AttributeError:
audio = file[1] / 32768.0
if len(audio.shape) == 2:
audio = np.mean(audio, -1)
return librosa.resample(audio, orig_sr=file[0], target_sr=16000)
except Exception as e: except Exception as e:
raise RuntimeError(f"Failed to load audio: {e}") raise RuntimeError(f"Failed to load audio: {e}")
return np.frombuffer(out, np.float32).flatten()