NikkeDoy/SISU
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

⚗️ | Experimenting, again.

Browse Source
This commit is contained in:
NikkeDoy
2024-12-26 04:00:24 +02:00
parent 2ff45de22d
commit 89f8c68986
4 changed files with 49 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
data.py
View File

@@ -13,7 +13,8 @@ class AudioDataset(Dataset):
audio_sample_rates = [11025]
def __init__(self, input_dir):
self.input_files = [os.path.join(input_dir, f) for f in os.listdir(input_dir) if f.endswith('.wav')]
self.input_files = [os.path.join(root, f) for root, _, files in os.walk(input_dir) for f in files if f.endswith('.wav')]
def __len__(self):
return len(self.input_files)
@@ -25,7 +26,10 @@ class AudioDataset(Dataset):
# Generate low-quality audio with random downsampling
mangled_sample_rate = random.choice(self.audio_sample_rates)
resample_transform = torchaudio.transforms.Resample(original_sample_rate, mangled_sample_rate)
low_quality_audio = resample_transform(high_quality_audio)
resample_transform_low = torchaudio.transforms.Resample(original_sample_rate, mangled_sample_rate)
low_quality_audio = resample_transform_low(high_quality_audio)
resample_transform_high = torchaudio.transforms.Resample(mangled_sample_rate, original_sample_rate)
low_quality_audio = resample_transform_high(low_quality_audio)
return (AudioUtils.stereo_tensor_to_mono(high_quality_audio), original_sample_rate), (AudioUtils.stereo_tensor_to_mono(low_quality_audio), mangled_sample_rate)