1
0
mirror of https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI.git synced 2026-06-05 01:10:22 +08:00

Merge pull request #4 from alexlnkp/formatter-dev

chore(format): run black on dev
This commit is contained in:
Alex Murkoff
2024-06-11 18:16:52 +07:00
committed by GitHub
4 changed files with 33 additions and 19 deletions

View File

@@ -41,10 +41,12 @@ def load_audio(file: str, sr: int) -> np.ndarray:
try:
container = av.open(file)
resampler = AudioResampler(format='fltp', layout='mono', rate=sr)
resampler = AudioResampler(format="fltp", layout="mono", rate=sr)
# AV stores duration in nanoseconds
decoded_audio = (((container.duration * sr / container.bit_rate) // 1_000_000) + 1)*[]
decoded_audio = (
((container.duration * sr / container.bit_rate) // 1_000_000) + 1
) * []
for frame in container.decode(audio=0):
frame.pts = None # Clear presentation timestamp to avoid resampling issues
@@ -57,17 +59,19 @@ def load_audio(file: str, sr: int) -> np.ndarray:
return np.frombuffer(audio, dtype=np.float32).flatten()
def downsample_audio(input_path: str, output_path: str, format: str) -> None:
if not os.path.exists(input_path): return
if not os.path.exists(input_path):
return
input_container = av.open(input_path)
output_container = av.open(output_path, 'w')
output_container = av.open(output_path, "w")
# Create a stream in the output container
input_stream = input_container.streams.audio[0]
output_stream = output_container.add_stream(format)
output_stream.bit_rate = 128_000 # 128kb/s (equivalent to -q:a 2)
output_stream.bit_rate = 128_000 # 128kb/s (equivalent to -q:a 2)
# Copy packets from the input file to the output file
for packet in input_container.demux(input_stream):
@@ -77,26 +81,30 @@ def downsample_audio(input_path: str, output_path: str, format: str) -> None:
for packet in output_stream.encode():
output_container.mux(packet)
# Close the containers
input_container.close()
output_container.close()
try: # Remove the original file
try: # Remove the original file
os.remove(input_path)
except Exception as e:
print(f"Failed to remove the original file: {e}")
def resample_audio(input_path: str, output_path: str, codec: str, format: str, sr: int, layout: str) -> None:
if not os.path.exists(input_path): return
def resample_audio(
input_path: str, output_path: str, codec: str, format: str, sr: int, layout: str
) -> None:
if not os.path.exists(input_path):
return
input_container = av.open(input_path)
output_container = av.open(output_path, 'w')
output_container = av.open(output_path, "w")
# Create a stream in the output container
input_stream = input_container.streams.audio[0]
output_stream = output_container.add_stream(codec, rate=sr, layout=layout)
resampler = AudioResampler(format, layout, sr)
# Copy packets from the input file to the output file
@@ -110,23 +118,25 @@ def resample_audio(input_path: str, output_path: str, codec: str, format: str, s
for packet in output_stream.encode():
output_container.mux(packet)
# Close the containers
input_container.close()
output_container.close()
try: # Remove the original file
try: # Remove the original file
os.remove(input_path)
except Exception as e:
print(f"Failed to remove the original file: {e}")
def get_audio_properties(input_path: str) -> Tuple:
container = av.open(input_path)
audio_stream = next(s for s in container.streams if s.type == 'audio')
channels = 1 if audio_stream.layout == 'mono' else 2
audio_stream = next(s for s in container.streams if s.type == "audio")
channels = 1 if audio_stream.layout == "mono" else 2
rate = audio_stream.base_rate
container.close()
return channels, rate
def clean_path(path: str) -> Path:
return Path(path.strip(' "\n')).resolve()

View File

@@ -224,6 +224,7 @@ class Predictor:
downsample_audio(path_vocal, opt_path_vocal, format)
downsample_audio(path_other, opt_path_other, format)
class MDXNetDereverb:
def __init__(self, chunks, device):
self.onnx = "assets/uvr5_weights/onnx_dereverb_By_FoxJoy"

View File

@@ -50,7 +50,9 @@ def uvr(model_name, inp_root, save_root_vocal, paths, save_root_ins, agg, format
# Check the audio stream's properties
if channels == 2 and rate == 44100:
pre_fun._path_audio_(inp_path, save_root_ins, save_root_vocal, format0, is_hp3=is_hp3)
pre_fun._path_audio_(
inp_path, save_root_ins, save_root_vocal, format0, is_hp3=is_hp3
)
need_reformat = 0
done = 1
except Exception as e:
@@ -61,7 +63,7 @@ def uvr(model_name, inp_root, save_root_vocal, paths, save_root_ins, agg, format
os.path.join(os.environ["TEMP"]),
os.path.basename(inp_path),
)
resample_audio(inp_path, tmp_path, 'pcm_s16le', 's16', 44100, 'stereo')
resample_audio(inp_path, tmp_path, "pcm_s16le", "s16", 44100, "stereo")
inp_path = tmp_path
try:
if done == 0:

View File

@@ -184,6 +184,7 @@ class AudioPre:
opt_format_path = path[:-4] + ".%s" % format
downsample_audio(path, opt_format_path, format)
class AudioPreDeEcho:
def __init__(self, agg, model_path, device, is_half, tta=False):
self.model_path = model_path