Fix typos (#3984)

* Fix

* Fix

audio/paddleaudio/backends/soundfile_backend.py

@@ -183,7 +183,7 @@ def soundfile_save(y: np.ndarray, sr: int, file: os.PathLike) -> None:
     Args:
         y (np.ndarray): Input waveform array in 1D or 2D.
         sr (int): Sample rate.
-        file (os.PathLike): Path of auido file to save.
+        file (os.PathLike): Path of audio file to save.
     """
     if not file.endswith('.wav'):
         raise ParameterError(
@@ -216,10 +216,10 @@ def soundfile_load(
         duration: Optional[int]=None,
         dtype: str='float32',
         resample_mode: str='kaiser_fast') -> Tuple[np.ndarray, int]:
-    """Load audio file from disk. This function loads audio from disk using using audio beackend.
+    """Load audio file from disk. This function loads audio from disk using using audio backend.
 
     Args:
-        file (os.PathLike): Path of auido file to load.
+        file (os.PathLike): Path of audio file to load.
         sr (Optional[int], optional): Sample rate of loaded waveform. Defaults to None.
         mono (bool, optional): Return waveform with mono channel. Defaults to True.
         merge_type (str, optional): Merge type of multi-channels waveform. Defaults to 'average'.
@@ -250,14 +250,14 @@ def soundfile_load(
     if normal:
         y = normalize(y, norm_type, norm_mul_factor)
     elif dtype in ['int8', 'int16']:
-        # still need to do normalization, before depth convertion
+        # still need to do normalization, before depth conversion
         y = normalize(y, 'linear', 1.0)
 
     y = depth_convert(y, dtype)
     return y, r
 
 
-#the code below token form: https://github.com/pytorch/audio/blob/main/torchaudio/backend/soundfile_backend.py with modificaion.
+#The code below is taken from: https://github.com/pytorch/audio/blob/main/torchaudio/backend/soundfile_backend.py, with some modifications.
 
 
 def _get_subtype_for_wav(dtype: paddle.dtype,
@@ -382,7 +382,7 @@ def save(
         channels_first (bool, optional): If ``True``, the given tensor is interpreted as `[channel, time]`,
             otherwise `[time, channel]`.
         compression (float of None, optional): Not used.
-            It is here only for interface compatibility reson with "sox_io" backend.
+            It is here only for interface compatibility reason with "sox_io" backend.
         format (str or None, optional): Override the audio format.
             When ``filepath`` argument is path-like object, audio format is
             inferred from file extension. If the file extension is missing or
@@ -394,8 +394,8 @@ def save(
             Valid values are ``"wav"``, ``"ogg"``, ``"vorbis"``,
             ``"flac"`` and ``"sph"``.
         encoding (str or None, optional): Changes the encoding for supported formats.
-            This argument is effective only for supported formats, sush as
-            ``"wav"``, ``""flac"`` and ``"sph"``. Valid values are;
+            This argument is effective only for supported formats, such as
+            ``"wav"``, ``""flac"`` and ``"sph"``. Valid values are:
 
                 - ``"PCM_S"`` (signed integer Linear PCM)
                 - ``"PCM_U"`` (unsigned integer Linear PCM)

audio/paddleaudio/compliance/librosa.py

@@ -626,7 +626,7 @@ def mu_decode(y: np.ndarray, mu: int=255, quantized: bool=True) -> np.ndarray:
 def _randint(high: int) -> int:
     """Generate one random integer in range [0 high)
 
-     This is a helper function for random data augmentaiton
+     This is a helper function for random data augmentation
     """
     return int(np.random.randint(0, high=high))
 
@@ -659,7 +659,7 @@ def depth_augment(y: np.ndarray,
 def adaptive_spect_augment(spect: np.ndarray,
                            tempo_axis: int=0,
                            level: float=0.1) -> np.ndarray:
-    """Do adpative spectrogram augmentation. The level of the augmentation is gowern by the paramter level, ranging from 0 to 1, with 0 represents no augmentation.
+    """Do adaptive spectrogram augmentation. The level of the augmentation is govern by the parameter level, ranging from 0 to 1, with 0 represents no augmentation.
 
     Args:
         spect (np.ndarray): Input spectrogram.
@@ -711,9 +711,9 @@ def spect_augment(spect: np.ndarray,
         spect (np.ndarray): Input spectrogram.
         tempo_axis (int, optional): Indicate the tempo axis. Defaults to 0.
         max_time_mask (int, optional): Maximum number of time masking. Defaults to 3.
-        max_freq_mask (int, optional): Maximum number of frenquence masking. Defaults to 3.
+        max_freq_mask (int, optional): Maximum number of frequency masking. Defaults to 3.
         max_time_mask_width (int, optional): Maximum width of time masking. Defaults to 30.
-        max_freq_mask_width (int, optional): Maximum width of frenquence masking. Defaults to 20.
+        max_freq_mask_width (int, optional): Maximum width of frequency masking. Defaults to 20.
 
     Returns:
         np.ndarray: The augmented spectrogram.

audio/paddleaudio/src/pybind/sox/utils.cpp

@@ -449,7 +449,7 @@ unsigned get_precision(const std::string filetype, py::dtype dtype) {
     return SOX_UNSPEC;
   if (filetype == "wav" || filetype == "amb") {
     switch (dtype.num()) {
-      case 1: // byte in numpy dype num
+      case 1: // byte in numpy dtype num
         return 8;
       case 3: // short, in numpy dtype num
         return 16;

audio/tests/backends/soundfile/save_test.py

@@ -58,7 +58,7 @@ class MockedSaveTest(unittest.TestCase):
             encoding=encoding,
             bits_per_sample=bits_per_sample, )
 
-        # on +Py3.8 call_args.kwargs is more descreptive
+        # on +Py3.8 call_args.kwargs is more descriptive
         args = mocked_write.call_args[1]
         assert args["file"] == filepath
         assert args["samplerate"] == sample_rate

dataset/chime3_background/chime3_background.py

@@ -58,7 +58,7 @@ def download(url, md5sum, target_dir, filename=None):
     if not (os.path.exists(filepath) and md5file(filepath) == md5sum):
         print("Downloading %s ..." % url)
         wget.download(url, target_dir)
-        print("\nMD5 Chesksum %s ..." % filepath)
+        print("\nMD5 Checksum %s ..." % filepath)
         if not md5file(filepath) == md5sum:
             raise RuntimeError("MD5 checksum failed.")
     else:

dataset/mini_librispeech/mini_librispeech.py

@@ -108,7 +108,7 @@ def create_manifest(data_dir, manifest_path):
 
 
 def prepare_dataset(url, md5sum, target_dir, manifest_path):
-    """Download, unpack and create summmary manifest file.
+    """Download, unpack and create summary manifest file.
     """
     if not os.path.exists(os.path.join(target_dir, "LibriSpeech")):
         # download