sonusai 0.14.1__py3-none-any.whl → 0.14.2__py3-none-any.whl

sonusai/mixture/audio.py

@@ -59,6 +59,7 @@ def get_duration(audio: AudioT) -> float:
     :return: Duration of audio in seconds
     """
     from .constants import SAMPLE_RATE
+
     return len(audio) / SAMPLE_RATE
 
 
@@ -66,14 +67,15 @@ def validate_input_file(input_filepath: str) -> None:
     from os.path import exists
     from os.path import splitext
 
-    from torchaudio.utils.sox_utils import list_read_formats
+    from soundfile import available_formats
 
     from sonusai import SonusAIError
+
     if not exists(input_filepath):
         raise SonusAIError(f'input_filepath {input_filepath} does not exist.')
 
     ext = splitext(input_filepath)[1][1:].lower()
-    read_formats = list_read_formats()
+    read_formats = [item.lower() for item in available_formats().keys()]
     if ext not in read_formats:
         raise SonusAIError(f'This installation of SoX cannot process .{ext} files')
 
@@ -86,6 +88,7 @@ def read_audio(name: Location) -> AudioT:
     :return: Array of time domain audio data
     """
     from .torchaudio_audio import read_torchaudio_audio
+
     return read_torchaudio_audio(name)
 
 
@@ -97,4 +100,5 @@ def read_ir(name: Location) -> ImpulseResponseData:
     :return: ImpulseResponseData object
     """
     from .torchaudio_audio import read_torchaudio_ir
+
     return read_torchaudio_ir(name)

sonusai/mixture/torchaudio_audio.py

@@ -21,7 +21,7 @@ def read_torchaudio_ir(name: Location) -> ImpulseResponseData:
 
     # Read impulse response data from audio file
     try:
-        raw, sample_rate = torchaudio.load(expanded_name)
+        raw, sample_rate = torchaudio.load(expanded_name, backend='soundfile')
     except Exception as e:
         if name != expanded_name:
             raise SonusAIError(f'Error reading {name} (expanded: {expanded_name}): {e}')
@@ -58,7 +58,7 @@ def read_torchaudio_audio(name: Location) -> AudioT:
     expanded_name, _ = tokenized_expand(name)
 
     try:
-        out, samplerate = torchaudio.load(expanded_name)
+        out, samplerate = torchaudio.load(expanded_name, backend='soundfile')
         out = torch.reshape(out[0, :], (1, out.size()[1]))
 
         if not samplerate == SAMPLE_RATE:

{sonusai-0.14.1.dist-info → sonusai-0.14.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sonusai
-Version: 0.14.1
+Version: 0.14.2
 Summary: Framework for building deep neural network models for sound, speech, and voice AI
 Home-page: https://aaware.com
 License: GPL-3.0-only
@@ -34,6 +34,7 @@ Requires-Dist: pystoi (>=0.3.3,<0.4.0)
 Requires-Dist: requests (>=2.31.0,<3.0.0)
 Requires-Dist: scikit-learn (>=1.3.1,<2.0.0)
 Requires-Dist: sh (>=2.0.6,<3.0.0)
+Requires-Dist: soundfile (>=0.12.1,<0.13.0)
 Requires-Dist: sox (>=1.4.1,<2.0.0)
 Requires-Dist: speechrecognition (>=3.10.0,<4.0.0)
 Requires-Dist: sqlalchemy[mypy] (>=2.0.22,<3.0.0)

{sonusai-0.14.1.dist-info → sonusai-0.14.2.dist-info}/RECORD

@@ -33,7 +33,7 @@ sonusai/metrics/confusion_matrix_summary.py,sha256=3qg6TMKjJeHtNjj2YnNjPFSlMrQXt
 sonusai/metrics/one_hot.py,sha256=lq58zKw0X9sdhJYGEldAkxPFqP3UOYpG_KdxkGHF_3c,13540
 sonusai/metrics/snr_summary.py,sha256=P4U5_Xr7v9F8kF-rZBnpsVNt3p42rIVS6zmch8yfVfg,5575
 sonusai/mixture/__init__.py,sha256=xlGw2FXoMZm2ra97GVfpJ-OTOp10d4dly8AXe8eJwhI,5294
-sonusai/mixture/audio.py,sha256=13zBg-ix3SC7xzFFX9WcGUuWowodRVI6pryWRmH7YmY,3221
+sonusai/mixture/audio.py,sha256=3pat-AIG_FXiGr3aPRa7DSLzolH3PodVDtve-xUuXfk,3242
 sonusai/mixture/augmentation.py,sha256=HwYUJCSmRBWhdnzqKz5zZnMANT83GzJkDrPcWUm6jbg,10884
 sonusai/mixture/class_count.py,sha256=27YDu1puarhp7Rd4EYWGJ-FHP8rAYGd55I6abGqCscY,988
 sonusai/mixture/config.py,sha256=QrasMP-2NGocse2rF_oYkRluDDPo-czFLDEwKtQ8A54,23629
@@ -50,7 +50,7 @@ sonusai/mixture/spectral_mask.py,sha256=qHR2DBpbtz4u1o9sdFMRsUDVUjbof_MRKPW8uY4R
 sonusai/mixture/target_class_balancing.py,sha256=P3gLe2SFos5_N2LWiVFwD-fa_imZH2f1qBiI55BeqXI,4768
 sonusai/mixture/targets.py,sha256=n7PenQuU0pPM_LLXJHmUZ3VeSGDEk7Kdf8y473Xdm6Q,7395
 sonusai/mixture/tokenized_shell_vars.py,sha256=gCxw8SQUcal6mqWKF7hOBTgSQmbJUk1nT0Gn3H8GA0U,4705
-sonusai/mixture/torchaudio_audio.py,sha256=HL11-1_UK9QuvCP17cAnlfsBLZzR0aqLif7gRexxySM,2323
+sonusai/mixture/torchaudio_audio.py,sha256=qMYXeOSI8U8zaT9x0knPg1dHWzYmswZk7oFGAMG0Jks,2365
 sonusai/mixture/torchaudio_augmentation.py,sha256=LrG19X71UYKMr69WNgJs2R4OTt1QBYu_h8WL5a4ERyE,4462
 sonusai/mixture/truth.py,sha256=Is-nqLXIBM7wjYbS6yzy8mnR8JqxwSabnVHsza0rh_E,1427
 sonusai/mixture/truth_functions/__init__.py,sha256=82lKYHhLy8KW3gHngrocoqwupGVLVsWdIXdYs3vhjOc,359
@@ -114,7 +114,7 @@ sonusai/utils/trim_docstring.py,sha256=dSrtiRsEN4wkkvKBp6WDr13RUypfqZzgH_jOBLs1o
 sonusai/utils/wave.py,sha256=OZe8iVLbKSFv_GdQzLD9hJdBiqimK4FxJ0lVoDbbiqQ,572
 sonusai/utils/yes_or_no.py,sha256=eMLXBVH0cEahiXY4W2KNORmwNQ-ba10eRtldh0y4NYg,263
 sonusai/vars.py,sha256=m2AefF0m5bXWGXpJj8Pi42zWL2ydeEj7bkak3GrtMyM,940
-sonusai-0.14.1.dist-info/METADATA,sha256=_zSNpDBiIWQhEaFz7m7RzfaeI_ISMZX1WTk5Fa_dkI8,2775
-sonusai-0.14.1.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-sonusai-0.14.1.dist-info/entry_points.txt,sha256=zMNjEphEPO6B3cD1GNpit7z-yA9tUU5-j3W2v-UWstU,92
-sonusai-0.14.1.dist-info/RECORD,,
+sonusai-0.14.2.dist-info/METADATA,sha256=RR8bQ-ZUGFqZZJID86OMAAM6N0h7MYpfwJlDYf4t0v4,2819
+sonusai-0.14.2.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+sonusai-0.14.2.dist-info/entry_points.txt,sha256=zMNjEphEPO6B3cD1GNpit7z-yA9tUU5-j3W2v-UWstU,92
+sonusai-0.14.2.dist-info/RECORD,,