Skip to content

Fix invalid escape sequences in text normalization and models #3709

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
MBK-fr wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix invalid escape sequences in text normalization and models #3709

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
2 changes: 1 addition & 1 deletion fun_text_processing/text_normalization/normalize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -351,7 +351,7 @@ def split_text_into_sentences(self, text: str) -> List[str]:
upper_case_unicode = "\u0410-\u042F"

# Read and split transcript by utterance (roughly, sentences)
split_pattern = f"(?<!\w\.\w.)(?<![A-Z{upper_case_unicode}][a-z{lower_case_unicode}]+\.)(?<![A-Z{upper_case_unicode}]\.)(?<=\.|\?|\!|\.”|\?”\!”)\s(?![0-9]+[a-z]*\.)"
split_pattern = f"(?<!\\w\\.\\w.)(?<![A-Z{upper_case_unicode}][a-z{lower_case_unicode}]+\\.)(?<![A-Z{upper_case_unicode}]\\.)(?<=\\.|\\?|\\!|\\.”|\\?”\\!”)\\s(?![0-9]+[a-z]*\\.)"

sentences = regex.split(split_pattern, text)
return sentences
Expand Down
12 changes: 6 additions & 6 deletions funasr/models/fsmn_kws/encoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,7 @@ def to_pytorch_net(self, fread):
dtype=torch.float32)
for i in range(self.output_dim):
line = fread.readline()
splits = line.strip().strip('\[\]').strip().split()
splits = line.strip().strip('\\[\\]').strip().split()
assert len(splits) == self.input_dim
cols = torch.tensor([float(item) for item in splits],
dtype=torch.float32)
Expand Down Expand Up @@ -160,7 +160,7 @@ def to_pytorch_net(self, fread):
dtype=torch.float32)
for i in range(self.output_dim):
line = fread.readline()
splits = line.strip().strip('\[\]').strip().split()
splits = line.strip().strip('\\[\\]').strip().split()
assert len(splits) == self.input_dim
cols = torch.tensor([float(item) for item in splits],
dtype=torch.float32)
Expand All @@ -171,7 +171,7 @@ def to_pytorch_net(self, fread):
linear_bias = self.state_dict()['linear.bias']
#print(linear_bias.shape)
bias_line = fread.readline()
splits = bias_line.strip().strip('\[\]').strip().split()
splits = bias_line.strip().strip('\\[\\]').strip().split()
assert len(splits) == self.output_dim
new_bias = torch.tensor([float(item) for item in splits],
dtype=torch.float32)
Expand Down Expand Up @@ -331,7 +331,7 @@ def to_pytorch_net(self, fread):
self.dim = int(fsmn_split[1])

params_line = fread.readline()
params_split = params_line.strip().strip('\[\]').strip().split()
params_split = params_line.strip().strip('\\[\\]').strip().split()
assert len(params_split) == 12
assert params_split[0] == '<LearnRateCoef>'
assert params_split[2] == '<LOrder>'
Expand All @@ -352,7 +352,7 @@ def to_pytorch_net(self, fread):
for i in range(self.lorder):
print('read conv_left weight -- %d' % i)
line = fread.readline()
splits = line.strip().strip('\[\]').strip().split()
splits = line.strip().strip('\\[\\]').strip().split()
assert len(splits) == self.dim
cols = torch.tensor([float(item) for item in splits],
dtype=torch.float32)
Expand All @@ -375,7 +375,7 @@ def to_pytorch_net(self, fread):
for i in range(self.rorder):
print('read conv_right weight -- %d' % i)
line = fread.readline()
splits = line.strip().strip('\[\]').strip().split()
splits = line.strip().strip('\\[\\]').strip().split()
assert len(splits) == self.dim
cols = torch.tensor([float(item) for item in splits],
dtype=torch.float32)
Expand Down
4 changes: 2 additions & 2 deletions funasr/models/fun_asr_nano/tools/format5res.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -320,8 +320,8 @@ def all_convert(content):
continue
name = tmp[0]
content = tmp[1]
name = re.sub("\.pcm", "", name)
name = re.sub("\.wav", "", name)
name = re.sub("\\.pcm", "", name)
name = re.sub("\\.wav", "", name)
content = recoformat(content)
content = numbersingle(content)
content = ch_number2digit(content)
Expand Down