1
0
mirror of synced 2024-12-11 23:36:04 +01:00
Retrieval-based-Voice-Conve.../infer/lib/audio.py
github-actions[bot] 1696c5356b
chore(sync): merge dev into main (#1399)
* Update mdxnet.py

* Update modules.py

* Rename preprocess.py to vr.py

* Add files via upload

* deps: add av lib (#1391)

* Add files via upload

* chore(format): run black on dev (#1398)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

---------

Co-authored-by: RVC-Boss <129054828+RVC-Boss@users.noreply.github.com>
Co-authored-by: Hiroto N <hironow365@gmail.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2023-10-08 18:54:58 +08:00

74 lines
1.8 KiB
Python

import os
import traceback
import librosa
import numpy as np
import av
from io import BytesIO
def wav2(i, o, format):
inp = av.open(i, "rb")
if format == "m4a":
format = "mp4"
out = av.open(o, "wb", format=format)
if format == "ogg":
format = "libvorbis"
if format == "mp4":
format = "aac"
ostream = out.add_stream(format)
for frame in inp.decode(audio=0):
for p in ostream.encode(frame):
out.mux(p)
for p in ostream.encode(None):
out.mux(p)
out.close()
inp.close()
def audio2(i, o, format, sr):
inp = av.open(i, "rb")
out = av.open(o, "wb", format=format)
if format == "ogg":
format = "libvorbis"
if format == "f32le":
format = "pcm_f32le"
ostream = out.add_stream(format, channels=1)
ostream.sample_rate = sr
for frame in inp.decode(audio=0):
for p in ostream.encode(frame):
out.mux(p)
out.close()
inp.close()
def load_audio(file, sr):
file = (
file.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
) # 防止小白拷路径头尾带了空格和"和回车
if os.path.exists(file) == False:
raise RuntimeError(
"You input a wrong audio path that does not exists, please fix it!"
)
try:
with open(file, "rb") as f:
with BytesIO() as out:
audio2(f, out, "f32le", sr)
return np.frombuffer(out.getvalue(), 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:
raise RuntimeError(traceback.format_exc())