Skip to content

Fix Loudness Issue #232

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Fix Loudness Issue #232

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f0ceffc
Merge remote-tracking branch 'zgldh/main'
alastorid Dec 25, 2024
76c3187
SAY GOODBYE TO CLIPPING
alastorid Dec 25, 2024
df784b7
Rework fix_loudness to normalize_loudness to resolve potential issues
alastorid Jan 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion melo/api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,7 +122,7 @@ def tts_to_file(self, text, speaker_id, output_path=None, sdp_ratio=0.2, noise_s
)[0][0, 0].data.cpu().float().numpy()
del x_tst, tones, lang_ids, bert, ja_bert, x_tst_lengths, speakers
#
audio_list.append(audio)
audio_list.append(utils.normalize_loudness(audio))
torch.cuda.empty_cache()
audio = self.audio_numpy_concat(audio_list, sr=self.hps.data.sampling_rate, speed=speed)

Expand Down
20 changes: 19 additions & 1 deletion melo/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,25 @@

logger = logging.getLogger(__name__)


def normalize_loudness(audio):
max_val = np.max(np.abs(audio))
if max_val == 0:
return audio
scale_factor = (1 - 1e-6) / max_val
normalized_audio = audio * scale_factor

if False:
print(f'--- normalize ---')
print(f"Before normalization:")
print(f" Min value: {np.min(audio)}")
print(f" Max value: {np.max(audio)}")
print(f" Length: {len(audio)}")
print(f"After normalization:")
print(f" Min value: {np.min(normalized_audio)}")
print(f" Max value: {np.max(normalized_audio)}")
print(f" Length: {len(normalized_audio)}")

return normalized_audio

def get_text_for_tts_infer(text, language_str, hps, device, symbol_to_id=None):
norm_text, phone, tone, word2ph = clean_text(text, language_str)
Expand Down