Skip to content

Commit 50ef94b

Browse files
co63occo63oc
authored
Fix typos (#4024)
* Fix * Fix
1 parent c2dc4da commit 50ef94b

File tree

34 files changed

+51
-52
lines changed

34 files changed

+51
-52
lines changed

‎audio/paddleaudio/compliance/kaldi.py

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -233,7 +233,7 @@ def spectrogram(waveform: Tensor,
233233
round_to_power_of_two (bool, optional): If True, round window size to power of two by zero-padding input
234234
to FFT. Defaults to True.
235235
sr (int, optional): Sample rate of input waveform. Defaults to 16000.
236-
snip_edges (bool, optional): Drop samples in the end of waveform that cann't fit a signal frame when it
236+
snip_edges (bool, optional): Drop samples in the end of waveform that can't fit a signal frame when it
237237
is set True. Otherwise performs reflect padding to the end of waveform. Defaults to True.
238238
subtract_mean (bool, optional): Whether to subtract mean of feature files. Defaults to False.
239239
window_type (str, optional): Choose type of window for FFT computation. Defaults to "povey".
@@ -443,7 +443,7 @@ def fbank(waveform: Tensor,
443443
round_to_power_of_two (bool, optional): If True, round window size to power of two by zero-padding input
444444
to FFT. Defaults to True.
445445
sr (int, optional): Sample rate of input waveform. Defaults to 16000.
446-
snip_edges (bool, optional): Drop samples in the end of waveform that cann't fit a signal frame when it
446+
snip_edges (bool, optional): Drop samples in the end of waveform that can't fit a signal frame when it
447447
is set True. Otherwise performs reflect padding to the end of waveform. Defaults to True.
448448
subtract_mean (bool, optional): Whether to subtract mean of feature files. Defaults to False.
449449
use_energy (bool, optional): Add an dimension with energy of spectrogram to the output. Defaults to False.
@@ -566,7 +566,7 @@ def mfcc(waveform: Tensor,
566566
round_to_power_of_two (bool, optional): If True, round window size to power of two by zero-padding input
567567
to FFT. Defaults to True.
568568
sr (int, optional): Sample rate of input waveform. Defaults to 16000.
569-
snip_edges (bool, optional): Drop samples in the end of waveform that cann't fit a signal frame when it
569+
snip_edges (bool, optional): Drop samples in the end of waveform that can't fit a signal frame when it
570570
is set True. Otherwise performs reflect padding to the end of waveform. Defaults to True.
571571
subtract_mean (bool, optional): Whether to subtract mean of feature files. Defaults to False.
572572
use_energy (bool, optional): Add an dimension with energy of spectrogram to the output. Defaults to False.

‎audio/paddleaudio/compliance/librosa.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -527,7 +527,7 @@ def melspectrogram(x: np.ndarray,
527527
if fmax is None:
528528
fmax = sr // 2
529529
if fmin < 0 or fmin >= fmax:
530-
raise ParameterError('fmin and fmax must statisfy 0<fmin<fmax')
530+
raise ParameterError('fmin and fmax must satisfy 0<fmin<fmax')
531531

532532
s = stft(
533533
x,

‎examples/aishell/asr3/cmd.sh

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -54,8 +54,8 @@ elif [ "${cmd_backend}" = sge ]; then
5454
# "sbatch" (Slurm)
5555
elif [ "${cmd_backend}" = slurm ]; then
5656
# The default setting is written in conf/slurm.conf.
57-
# You must change "-p cpu" and "-p gpu" for the "partion" for your environment.
58-
# To know the "partion" names, type "sinfo".
57+
# You must change "-p cpu" and "-p gpu" for the "partition" for your environment.
58+
# To know the "partition" names, type "sinfo".
5959
# You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*"
6060
# The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
6161

‎examples/librispeech/asr1/cmd.sh

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -54,8 +54,8 @@ elif [ "${cmd_backend}" = sge ]; then
5454
# "sbatch" (Slurm)
5555
elif [ "${cmd_backend}" = slurm ]; then
5656
# The default setting is written in conf/slurm.conf.
57-
# You must change "-p cpu" and "-p gpu" for the "partion" for your environment.
58-
# To know the "partion" names, type "sinfo".
57+
# You must change "-p cpu" and "-p gpu" for the "partition" for your environment.
58+
# To know the "partition" names, type "sinfo".
5959
# You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*"
6060
# The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
6161

‎examples/librispeech/asr2/cmd.sh

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -54,8 +54,8 @@ elif [ "${cmd_backend}" = sge ]; then
5454
# "sbatch" (Slurm)
5555
elif [ "${cmd_backend}" = slurm ]; then
5656
# The default setting is written in conf/slurm.conf.
57-
# You must change "-p cpu" and "-p gpu" for the "partion" for your environment.
58-
# To know the "partion" names, type "sinfo".
57+
# You must change "-p cpu" and "-p gpu" for the "partition" for your environment.
58+
# To know the "partition" names, type "sinfo".
5959
# You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*"
6060
# The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
6161

‎examples/librispeech/asr3/cmd.sh

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -54,8 +54,8 @@ elif [ "${cmd_backend}" = sge ]; then
5454
# "sbatch" (Slurm)
5555
elif [ "${cmd_backend}" = slurm ]; then
5656
# The default setting is written in conf/slurm.conf.
57-
# You must change "-p cpu" and "-p gpu" for the "partion" for your environment.
58-
# To know the "partion" names, type "sinfo".
57+
# You must change "-p cpu" and "-p gpu" for the "partition" for your environment.
58+
# To know the "partition" names, type "sinfo".
5959
# You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*"
6060
# The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
6161

‎examples/librispeech/asr4/cmd.sh

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -54,8 +54,8 @@ elif [ "${cmd_backend}" = sge ]; then
5454
# "sbatch" (Slurm)
5555
elif [ "${cmd_backend}" = slurm ]; then
5656
# The default setting is written in conf/slurm.conf.
57-
# You must change "-p cpu" and "-p gpu" for the "partion" for your environment.
58-
# To know the "partion" names, type "sinfo".
57+
# You must change "-p cpu" and "-p gpu" for the "partition" for your environment.
58+
# To know the "partition" names, type "sinfo".
5959
# You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*"
6060
# The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
6161

‎examples/librispeech/asr5/cmd.sh

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -54,8 +54,8 @@ elif [ "${cmd_backend}" = sge ]; then
5454
# "sbatch" (Slurm)
5555
elif [ "${cmd_backend}" = slurm ]; then
5656
# The default setting is written in conf/slurm.conf.
57-
# You must change "-p cpu" and "-p gpu" for the "partion" for your environment.
58-
# To know the "partion" names, type "sinfo".
57+
# You must change "-p cpu" and "-p gpu" for the "partition" for your environment.
58+
# To know the "partition" names, type "sinfo".
5959
# You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*"
6060
# The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
6161

‎examples/mustc/st1/cmd.sh

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -54,8 +54,8 @@ elif [ "${cmd_backend}" = sge ]; then
5454
# "sbatch" (Slurm)
5555
elif [ "${cmd_backend}" = slurm ]; then
5656
# The default setting is written in conf/slurm.conf.
57-
# You must change "-p cpu" and "-p gpu" for the "partion" for your environment.
58-
# To know the "partion" names, type "sinfo".
57+
# You must change "-p cpu" and "-p gpu" for the "partition" for your environment.
58+
# To know the "partition" names, type "sinfo".
5959
# You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*"
6060
# The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
6161

‎examples/other/ngram_lm/s0/local/kenlm_score_test.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -97,7 +97,7 @@ def test_full_scores_words():
9797
if w not in model:
9898
print('"{0}" is an OOV'.format(w))
9999
oov.append(w)
100-
# zh_giga.no_cna_cmn.prune01244.klm is chinese charactor LM
100+
# zh_giga.no_cna_cmn.prune01244.klm is chinese character LM
101101
assert oov == ["盘点", "不怕", "网站", "❗", "️", "海淘", "向来", "便宜", "保真",
102102
"！"], 'error oov'
103103

‎examples/ted_en_zh/st1/cmd.sh

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -54,8 +54,8 @@ elif [ "${cmd_backend}" = sge ]; then
5454
# "sbatch" (Slurm)
5555
elif [ "${cmd_backend}" = slurm ]; then
5656
# The default setting is written in conf/slurm.conf.
57-
# You must change "-p cpu" and "-p gpu" for the "partion" for your environment.
58-
# To know the "partion" names, type "sinfo".
57+
# You must change "-p cpu" and "-p gpu" for the "partition" for your environment.
58+
# To know the "partition" names, type "sinfo".
5959
# You can use "--gpu * " by default for slurm and it is interpreted as "--gres gpu:*"
6060
# The devices are allocated exclusively using "${CUDA_VISIBLE_DEVICES}".
6161

‎paddlespeech/dataset/aidatatang_200zh/aidatatang_200zh.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -62,7 +62,7 @@ def create_manifest(data_dir, manifest_path_prefix):
6262
if line == '':
6363
continue
6464
audio_id, text = line.split(' ', 1)
65-
# remove withespace, charactor text
65+
# remove withespace, character text
6666
text = ''.join(text.split())
6767
transcript_dict[audio_id] = text
6868

‎paddlespeech/dataset/aishell/aishell.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -65,7 +65,7 @@ def create_manifest(data_dir, manifest_path_prefix):
6565
if line == '':
6666
continue
6767
audio_id, text = line.split(' ', 1)
68-
# remove withespace, charactor text
68+
# remove withespace, character text
6969
text = ''.join(text.split())
7070
transcript_dict[audio_id] = text
7171

@@ -159,7 +159,7 @@ def check_dataset(data_dir):
159159
if line == '':
160160
continue
161161
audio_id, text = line.split(' ', 1)
162-
# remove withespace, charactor text
162+
# remove withespace, character text
163163
text = ''.join(text.split())
164164
transcript_dict[audio_id] = text
165165

‎paddlespeech/s2t/utils/error_rate.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -171,7 +171,7 @@ def wer(reference, hypothesis, ignore_case=False, delimiter=' '):
171171

172172

173173
def cer(reference, hypothesis, ignore_case=False, remove_space=False):
174-
"""Calculate charactor error rate (CER). CER compares reference text and
174+
"""Calculate character error rate (CER). CER compares reference text and
175175
hypothesis text in char-level. CER is defined as:
176176
177177
.. math::

‎paddlespeech/t2s/frontend/zh_frontend.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -523,7 +523,7 @@ def _g2p_assign(self,
523523
initials = []
524524
finals = []
525525

526-
# to charactor list
526+
# to character list
527527
words = self._split_word_to_char(words[0])
528528

529529
for pinyin, char in zip(pinyin_spec, words):

‎paddlespeech/t2s/utils/error_rate.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -159,7 +159,7 @@ def wer(reference, hypothesis, ignore_case=False, delimiter=' '):
159159

160160

161161
def cer(reference, hypothesis, ignore_case=False, remove_space=False):
162-
"""Calculate charactor error rate (CER). CER compares reference text and
162+
"""Calculate character error rate (CER). CER compares reference text and
163163
hypothesis text in char-level. CER is defined as:
164164
.. math::
165165
CER = (Sc + Dc + Ic) / Nc

‎runtime/engine/asr/decoder/ctc_prefix_beam_search_decoder.cc

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -157,7 +157,7 @@ void CTCPrefixBeamSearch::AdvanceDecoding(
157157
next_score.v_b = prefix_score.ViterbiScore() + prob;
158158
next_score.times_b = prefix_score.Times();
159159

160-
// Prefix not changed, copy the context from pefix
160+
// Prefix not changed, copy the context from prefix
161161
if (context_graph_ && !next_score.has_context) {
162162
next_score.CopyContext(prefix_score);
163163
next_score.has_context = true;
@@ -183,7 +183,7 @@ void CTCPrefixBeamSearch::AdvanceDecoding(
183183
}
184184
}
185185

186-
// Prefix not changed, copy the context from pefix
186+
// Prefix not changed, copy the context from prefix
187187
if (context_graph_ && !next_score1.has_context) {
188188
next_score1.CopyContext(prefix_score);
189189
next_score1.has_context = true;

‎runtime/engine/common/frontend/cmvn.cc

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -72,7 +72,7 @@ bool CMVN::Read(std::vector<BaseFloat>* feats) {
7272
return false;
7373
}
7474

75-
// appply cmvn
75+
// apply cmvn
7676
kaldi::Timer timer;
7777
Compute(feats);
7878
VLOG(1) << "CMVN::Read cost: " << timer.Elapsed() << " sec.";

‎runtime/engine/common/frontend/cmvn.h

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -29,7 +29,7 @@ class CMVN : public FrontendInterface {
2929
// the length of feats = feature_row * feature_dim,
3030
// the Matrix is squashed into Vector
3131
virtual bool Read(std::vector<kaldi::BaseFloat>* feats);
32-
// the dim_ is the feautre dim.
32+
// the dim_ is the feature dim.
3333
virtual size_t Dim() const { return dim_; }
3434
virtual void SetFinished() { base_extractor_->SetFinished(); }
3535
virtual bool IsFinished() const { return base_extractor_->IsFinished(); }

‎runtime/engine/common/frontend/db_norm.h

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -47,7 +47,7 @@ class DecibelNormalizer : public FrontendInterface {
4747
std::unique_ptr<FrontendInterface> base_extractor);
4848
virtual void Accept(const kaldi::VectorBase<kaldi::BaseFloat>& waves);
4949
virtual bool Read(kaldi::Vector<kaldi::BaseFloat>* waves);
50-
// noramlize audio, the dim is 1.
50+
// normalize audio, the dim is 1.
5151
virtual size_t Dim() const { return dim_; }
5252
virtual void SetFinished() { base_extractor_->SetFinished(); }
5353
virtual bool IsFinished() const { return base_extractor_->IsFinished(); }

‎runtime/engine/common/matrix/kaldi-matrix.cc

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -244,8 +244,8 @@ void MatrixBase<Real>::SymAddMat2(const Real alpha,
244244
/// function will produce NaN in the output. This is a bug in the
245245
/// ATLAS library. To overcome this, the AddMatMat function, which calls
246246
/// cblas_Xgemm(...) rather than cblas_Xsyrk(...), is used in this special
247-
/// sitation.
248-
/// Wei Shi: Note this bug is observerd for single precision matrix
247+
/// situation.
248+
/// Wei Shi: Note this bug is observed for single precision matrix
249249
/// on a 64-bit machine
250250
#ifdef HAVE_ATLAS
251251
if (transA == kTrans && num_rows_ >= 56) {
@@ -683,7 +683,7 @@ empty.
683683
if (V_in == NULL) tmpV.Resize(1, this->num_cols_); // work-space if V_in
684684
empty.
685685
686-
/// Impementation notes:
686+
/// Implementation notes:
687687
/// Lapack works in column-order, therefore the dimensions of *this are
688688
/// swapped as well as the U and V matrices.
689689
@@ -2378,7 +2378,7 @@ bool ReadHtk(std::istream &is, Matrix<Real> *M_ptr, HtkHeader *header_ptr)
23782378
Matrix<Real> &M = *M_ptr;
23792379
HtkHeader htk_hdr;
23802380
2381-
// TODO(arnab): this fails if the HTK file has CRC cheksum or is compressed.
2381+
// TODO(arnab): this fails if the HTK file has CRC checksum or is compressed.
23822382
is.read((char*)&htk_hdr, sizeof(htk_hdr)); // we're being really POSIX here!
23832383
if (is.fail()) {
23842384
KALDI_WARN << "Could not read header from HTK feature file ";

‎runtime/engine/common/matrix/kaldi-vector.cc

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -235,7 +235,7 @@ void VectorBase<Real>::CopyRowsFromMat(const MatrixBase<Real> &mat) {
235235
memcpy(inc_data, mat.Data(), cols * rows * sizeof(Real));
236236
} else {
237237
for (MatrixIndexT i = 0; i < rows; i++) {
238-
// copy the data to the propper position
238+
// copy the data to the proper position
239239
memcpy(inc_data, mat.RowData(i), cols * sizeof(Real));
240240
// set new copy position
241241
inc_data += cols;

‎runtime/engine/common/utils/file_utils.cc

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -44,7 +44,7 @@ std::string ReadFile2String(const std::string& path) {
4444
}
4545

4646
bool FileExists(const std::string& strFilename) {
47-
// this funciton if from:
47+
// this function if from:
4848
// https://github.com/kaldi-asr/kaldi/blob/master/src/fstext/deterministic-fst-test.cc
4949
struct stat stFileInfo;
5050
bool blnReturn;

‎runtime/engine/kaldi/lat/kaldi-lattice.cc

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -407,7 +407,7 @@ bool WriteLattice(std::ostream &os, bool binary, const Lattice &t) {
407407
if (os.fail())
408408
KALDI_WARN << "Stream failure detected.";
409409
// Write another newline as a terminating character. The read routine will
410-
// detect this [this is a Kaldi mechanism, not somethig in the original
410+
// detect this [this is a Kaldi mechanism, not something in the original
411411
// OpenFst code].
412412
os << '\n';
413413
return os.good();

‎runtime/examples/README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -34,7 +34,7 @@ bash run.sh --stop_stage 4
3434

3535
## Display Model with [Netron](https://github.com/lutzroeder/netron)
3636

37-
If you have a model, we can using this commnd to show model graph.
37+
If you have a model, we can using this commend to show model graph.
3838

3939
For example:
4040
```

‎runtime/examples/audio_classification/README.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -74,7 +74,7 @@ includes/
7474
#### set path
7575
push resource into android phone
7676

77-
1. change resource path in conf to gloabal path, such as:
77+
1. change resource path in conf to global path, such as:
7878

7979
[CONF]
8080
wav_normal=true
@@ -92,9 +92,9 @@ push resource into android phone
9292
high_freq=14000
9393
dither=0.0
9494
2. adb push conf label_list scp test.wav /data/local/tmp/
95-
3. set reource path in android demo(android_demo/app/src/main/cpp/native-lib.cpp) to actual path, such as:
95+
3. set resource path in android demo(android_demo/app/src/main/cpp/native-lib.cpp) to actual path, such as:
9696

9797
std::string conf_path = "/data/local/tmp/conf";
9898
std::string wav_path = "/data/local/tmp/test.wav";
9999

100-
4. excecute android_demo in android studio
100+
4. execute android_demo in android studio

‎runtime/examples/text_lm/local/mmseg.py

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -253,7 +253,6 @@ def createChunks(self):
253253
# print(word3.length, word3.text)
254254
if word3.length == -1:
255255
chunk = Chunk(word1, word2)
256-
# print("Ture")
257256
else:
258257
chunk = Chunk(word1, word2, word3)
259258
chunks.append(chunk)

‎runtime/patch/openfst/src/include/fst/flags.h

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -181,8 +181,8 @@ template <typename T>
181181
class FlagRegisterer {
182182
public:
183183
FlagRegisterer(const string &name, const FlagDescription<T> &desc) {
184-
auto registr = FlagRegister<T>::GetRegister();
185-
registr->SetDescription(name, desc);
184+
auto r = FlagRegister<T>::GetRegister();
185+
r->SetDescription(name, desc);
186186
}
187187

188188
private:

‎tests/test_tipc/conformer/scripts/aishell_tiny.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -62,7 +62,7 @@ def create_manifest(data_dir, manifest_path_prefix):
6262
if line == '':
6363
continue
6464
audio_id, text = line.split(' ', 1)
65-
# remove withespace, charactor text
65+
# remove withespace, character text
6666
text = ''.join(text.split())
6767
transcript_dict[audio_id] = text
6868

‎tests/unit/cli/aishell_test_prepare.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -63,7 +63,7 @@ def create_manifest(data_dir, manifest_path_prefix):
6363
if line == '':
6464
continue
6565
audio_id, text = line.split(' ', 1)
66-
# remove withespace, charactor text
66+
# remove withespace, character text
6767
text = ''.join(text.split())
6868
transcript_dict[audio_id] = text
6969

‎tests/unit/tts/test_snapshot.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@ def _test_snapshot():
3030
# use a simplest iterable object as dataloader
3131
dataloader = count()
3232

33-
# hack the training proecss: training does nothing except increse iteration
33+
# hack the training proecss: training does nothing except increase iteration
3434
updater = StandardUpdater(model, optimizer, dataloader=dataloader)
3535
updater.update_core = lambda x: None
3636

‎tools/extras/install_liblbfgs.sh

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,7 @@ cd liblbfgs-$VER
1717
./configure --prefix=`pwd`
1818
make
1919
# due to the liblbfgs project directory structure, we have to use -i
20-
# but the erros are completely harmless
20+
# but the errors are completely harmless
2121
make -i install
2222
cd ..
2323

‎utils/format_triplet_data.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -44,7 +44,7 @@
4444
# bpe
4545
add_arg('spm_model_prefix', str, None,
4646
"spm model prefix, spm_model_%(bpe_mode)_%(count_threshold), only need when `unit_type` is spm")
47-
add_arg('output_path', str, None, "filepath of formated manifest.", required=True)
47+
add_arg('output_path', str, None, "filepath of formatted manifest.", required=True)
4848
# yapf: disable
4949
args = parser.parse_args()
5050

‎utils/tokenizer.perl

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -79,7 +79,7 @@
7979
print " -b ... disable Perl buffering.\n";
8080
print " -time ... enable processing time calculation.\n";
8181
print " -penn ... use Penn treebank-like tokenization.\n";
82-
print " -protected FILE ... specify file with patters to be protected in tokenisation.\n";
82+
print " -protected FILE ... specify file with patterns to be protected in tokenisation.\n";
8383
print " -no-escape ... don't perform HTML escaping on apostrophy, quotes, etc.\n";
8484
exit;
8585
}

0 commit comments

Comments
 (0)