Skip to content
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

[tts] normalize wav max value to 1 in preprocess, test=tts #1887

Merged
merged 1 commit into from
May 12, 2022
Merged

[tts] normalize wav max value to 1 in preprocess, test=tts #1887

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 4 additions & 1 deletion paddlespeech/t2s/exps/fastspeech2/preprocess.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,8 +55,11 @@ def process_sentence(config: Dict[str, Any],
if utt_id in sentences:
# reading, resampling may occur
wav, _ = librosa.load(str(fp), sr=config.fs)
if len(wav.shape) != 1 or np.abs(wav).max() > 1.0:
if len(wav.shape) != 1:
return record
max_value = np.abs(wav).max()
if max_value > 1.0:
wav = wav / max_value
assert len(wav.shape) == 1, f"{utt_id} is not a mono-channel audio."
assert np.abs(wav).max(
) <= 1.0, f"{utt_id} is seems to be different that 16 bit PCM."
Expand Down
5 changes: 4 additions & 1 deletion paddlespeech/t2s/exps/gan_vocoder/preprocess.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,8 +47,11 @@ def process_sentence(config: Dict[str, Any],
if utt_id in sentences:
# reading, resampling may occur
y, _ = librosa.load(str(fp), sr=config.fs)
if len(y.shape) != 1 or np.abs(y).max() > 1.0:
if len(y.shape) != 1:
return record
max_value = np.abs(y).max()
if max_value > 1.0:
y = y / max_value
assert len(y.shape) == 1, f"{utt_id} is not a mono-channel audio."
assert np.abs(y).max(
) <= 1.0, f"{utt_id} is seems to be different that 16 bit PCM."
Expand Down
5 changes: 4 additions & 1 deletion paddlespeech/t2s/exps/speedyspeech/preprocess.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,8 +47,11 @@ def process_sentence(config: Dict[str, Any],
if utt_id in sentences:
# reading, resampling may occur
wav, _ = librosa.load(str(fp), sr=config.fs)
if len(wav.shape) != 1 or np.abs(wav).max() > 1.0:
if len(wav.shape) != 1:
return record
max_value = np.abs(wav).max()
if max_value > 1.0:
wav = wav / max_value
assert len(wav.shape) == 1, f"{utt_id} is not a mono-channel audio."
assert np.abs(wav).max(
) <= 1.0, f"{utt_id} is seems to be different that 16 bit PCM."
Expand Down
5 changes: 4 additions & 1 deletion paddlespeech/t2s/exps/tacotron2/preprocess.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,8 +51,11 @@ def process_sentence(config: Dict[str, Any],
if utt_id in sentences:
# reading, resampling may occur
wav, _ = librosa.load(str(fp), sr=config.fs)
if len(wav.shape) != 1 or np.abs(wav).max() > 1.0:
if len(wav.shape) != 1:
return record
max_value = np.abs(wav).max()
if max_value > 1.0:
wav = wav / max_value
assert len(wav.shape) == 1, f"{utt_id} is not a mono-channel audio."
assert np.abs(wav).max(
) <= 1.0, f"{utt_id} is seems to be different that 16 bit PCM."
Expand Down