Spaces:
Sleeping
Sleeping
File size: 2,118 Bytes
960cd20 |
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 |
"""
改用librosa。
（不是ffmpeg不好用，而是少装一个软件更有性价比）
"""
import librosa
import numpy as np
class DictToAttrRecursive(dict):
def __init__(self, input_dict):
super().__init__(input_dict)
for key, value in input_dict.items():
if isinstance(value, dict):
value = DictToAttrRecursive(value)
self[key] = value
setattr(self, key, value)
def __getattr__(self, item):
try:
return self[item]
except KeyError:
raise AttributeError(f"Attribute {item} not found")
def __setattr__(self, key, value):
if isinstance(value, dict):
value = DictToAttrRecursive(value)
super(DictToAttrRecursive, self).__setitem__(key, value)
super().__setattr__(key, value)
def __delattr__(self, item):
try:
del self[item]
except KeyError:
raise AttributeError(f"Attribute {item} not found")
# def load_audio(file, sr=16000):
# try:
# y, sr = librosa.load(file, sr=sr, dtype=np.float32)
# except Exception as e:
# raise RuntimeError(f"Failed to load audio: {e}")
#
# return y.flatten(), sr
# import ffmpeg
# import numpy as np
#
#
# def load_audio(file, sr):
# try:
# # https://github.com/openai/whisper/blob/main/whisper/audio.py#L26
# # This launches a subprocess to decode audio while down-mixing and resampling as necessary.
# # Requires the ffmpeg CLI and `ffmpeg-python` package to be installed.
# 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
# out, _ = (
# ffmpeg.input(file, threads=0)
# .output("-", format="f32le", acodec="pcm_f32le", ac=1, ar=sr)
# .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
# )
# except Exception as e:
# raise RuntimeError(f"Failed to load audio: {e}")
#
# return np.frombuffer(out, np.float32).flatten()
|