format

paddlespeech/cli/vector/infer.py

@@ -437,7 +437,9 @@ class VectorExecutor(BaseExecutor):
         if self.sample_rate != 16000 and self.sample_rate != 8000:
             logger.error(
                 "invalid sample rate, please input --sr 8000 or --sr 16000")
-            logger.error(f"The model sample rate: {self.sample_rate}, the external sample rate is: {sample_rate}")
+            logger.error(
+                f"The model sample rate: {self.sample_rate}, the external sample rate is: {sample_rate}"
+            )
             return False
 
         if isinstance(audio_file, (str, os.PathLike)):

paddlespeech/server/engine/vector/__init__.py

+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

paddlespeech/server/engine/vector/python/__init__.py

+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

paddlespeech/server/engine/vector/python/vector_engine.py

@@ -16,9 +16,9 @@ from collections import OrderedDict
 
 import numpy as np
 import paddle
-
 from paddleaudio.backends import load as load_audio
 from paddleaudio.compliance.librosa import melspectrogram
+
 from paddlespeech.cli.log import logger
 from paddlespeech.cli.vector.infer import VectorExecutor
 from paddlespeech.server.engine.base_engine import BaseEngine

speechx/speechx/decoder/param.h

@@ -21,7 +21,8 @@
 
 // feature
 DEFINE_bool(use_fbank, false, "False for fbank; or linear feature");
-// DEFINE_bool(to_float32, true, "audio convert to pcm32. True for linear feature, or fbank");
+// DEFINE_bool(to_float32, true, "audio convert to pcm32. True for linear
+// feature, or fbank");
 DEFINE_int32(num_bins, 161, "num bins of mel");
 DEFINE_string(cmvn_file, "", "read cmvn");
 DEFINE_double(streaming_chunk, 0.1, "streaming feature chunk size");

speechx/speechx/frontend/audio/fbank.cc

@@ -102,13 +102,16 @@ bool Fbank::Compute(const Vector<BaseFloat>& waves, Vector<BaseFloat>* feats) {
         // note: this online feature-extraction code does not support VTLN.
         RealFft(&window, true);
         kaldi::ComputePowerSpectrum(&window);
-        const kaldi::MelBanks &mel_bank = *(computer_.GetMelBanks(1.0));
+        const kaldi::MelBanks& mel_bank = *(computer_.GetMelBanks(1.0));
         SubVector<BaseFloat> power_spectrum(window, 0, window.Dim() / 2 + 1);
         if (!opts_.fbank_opts.use_power) {
             power_spectrum.ApplyPow(0.5);
         }
-        int32 mel_offset = ((opts_.fbank_opts.use_energy && !opts_.fbank_opts.htk_compat) ? 1 : 0);
-        SubVector<BaseFloat> mel_energies(this_feature, mel_offset, opts_.fbank_opts.mel_opts.num_bins);
+        int32 mel_offset =
+            ((opts_.fbank_opts.use_energy && !opts_.fbank_opts.htk_compat) ? 1
+                                                                           : 0);
+        SubVector<BaseFloat> mel_energies(
+            this_feature, mel_offset, opts_.fbank_opts.mel_opts.num_bins);
         mel_bank.Compute(power_spectrum, &mel_energies);
         mel_energies.ApplyFloor(1e-07);
         mel_energies.ApplyLog();

speechx/speechx/frontend/audio/feature_pipeline.cc

@@ -25,11 +25,11 @@ FeaturePipeline::FeaturePipeline(const FeaturePipelineOptions& opts) {
     unique_ptr<FrontendInterface> base_feature;
 
     if (opts.use_fbank) {
-        base_feature.reset(new ppspeech::Fbank(opts.fbank_opts,
-                              std::move(data_source)));
+        base_feature.reset(
+            new ppspeech::Fbank(opts.fbank_opts, std::move(data_source)));
     } else {
-        base_feature.reset(new ppspeech::LinearSpectrogram(opts.linear_spectrogram_opts,
-                              std::move(data_source)));
+        base_feature.reset(new ppspeech::LinearSpectrogram(
+            opts.linear_spectrogram_opts, std::move(data_source)));
     }
 
     unique_ptr<FrontendInterface> cmvn(

speechx/speechx/frontend/audio/feature_pipeline.h

@@ -18,10 +18,10 @@
 
 #include "frontend/audio/audio_cache.h"
 #include "frontend/audio/data_cache.h"
+#include "frontend/audio/fbank.h"
 #include "frontend/audio/feature_cache.h"
 #include "frontend/audio/frontend_itf.h"
 #include "frontend/audio/linear_spectrogram.h"
-#include "frontend/audio/fbank.h"
 #include "frontend/audio/normalizer.h"
 
 namespace ppspeech {