sonusai 0.17.2__py3-none-any.whl → 0.17.3__py3-none-any.whl

sonusai/audiofe.py

@@ -86,7 +86,7 @@ def main() -> None:
     from sonusai.utils import create_timestamp
     from sonusai.utils import get_input_devices
     from sonusai.utils import load_ort_session
-    from sonusai.utils import write_wav
+    from sonusai.utils import write_audio
 
     ts = create_timestamp()
     capture_name = f'audiofe_capture_{ts}'
@@ -121,7 +121,7 @@ def main() -> None:
             logger.exception(e)
             return
         # Only write if capture from device, not for file input
-        write_wav(capture_wav, capture_audio, SAMPLE_RATE)
+        write_audio(capture_wav, capture_audio, SAMPLE_RATE)
         logger.info('')
         logger.info(f'Wrote capture audio with shape {capture_audio.shape} to {capture_wav}')
 
@@ -175,7 +175,7 @@ def main() -> None:
             logger.info(f'Wrote predict with shape {predict.shape} to {h5_name}')
 
         predict_audio = get_audio_from_feature(feature=predict, feature_mode=feature_mode)
-        write_wav(predict_wav, predict_audio, SAMPLE_RATE)
+        write_audio(predict_wav, predict_audio, SAMPLE_RATE)
         logger.info(f'Wrote predict audio with shape {predict_audio.shape} to {predict_wav}')
         if debug:
             with h5py.File(h5_name, 'a') as f:

sonusai/calc_metric_spenh.py

@@ -718,7 +718,7 @@ def _process_mixture(mixid: int) -> tuple[pd.DataFrame, pd.DataFrame]:
     from sonusai.utils import reshape_outputs
     from sonusai.utils import stack_complex
     from sonusai.utils import unstack_complex
-    from sonusai.utils import write_wav
+    from sonusai.utils import write_audio
 
     mixdb = MP_GLOBAL.mixdb
     predict_location = MP_GLOBAL.predict_location
@@ -968,12 +968,12 @@ def _process_mixture(mixid: int) -> tuple[pd.DataFrame, pd.DataFrame]:
 
     # 7) write wav files
     if enable_wav:
-        write_wav(name=base_name + '_mixture.wav', audio=float_to_int16(mixture))
-        write_wav(name=base_name + '_target.wav', audio=float_to_int16(target))
-        # write_wav(name=base_name + '_target_fi.wav', audio=float_to_int16(target_fi))
-        write_wav(name=base_name + '_noise.wav', audio=float_to_int16(noise))
-        write_wav(name=base_name + '_target_est.wav', audio=float_to_int16(target_est_wav))
-        write_wav(name=base_name + '_noise_est.wav', audio=float_to_int16(noise_est_wav))
+        write_audio(name=base_name + '_mixture.wav', audio=float_to_int16(mixture))
+        write_audio(name=base_name + '_target.wav', audio=float_to_int16(target))
+        # write_audio(name=base_name + '_target_fi.wav', audio=float_to_int16(target_fi))
+        write_audio(name=base_name + '_noise.wav', audio=float_to_int16(noise))
+        write_audio(name=base_name + '_target_est.wav', audio=float_to_int16(target_est_wav))
+        write_audio(name=base_name + '_noise_est.wav', audio=float_to_int16(noise_est_wav))
 
         # debug code to test for perfect reconstruction of the extraction method
         # note both 75% olsa-hanns and 50% olsa-hann modes checked to have perfect reconstruction

sonusai/mixture/mixdb.py

@@ -10,7 +10,6 @@ from typing import Optional
 
 from praatio import textgrid
 from praatio.utilities.constants import Interval
-
 from sonusai.mixture.datatypes import AudioF
 from sonusai.mixture.datatypes import AudioT
 from sonusai.mixture.datatypes import AudiosF

sonusai/mixture/sox_augmentation.py

@@ -84,6 +84,7 @@ def apply_impulse_response(audio: AudioT, ir: ImpulseResponseData) -> AudioT:
     :return: Augmented audio
     """
     import math
+    from pathlib import Path
     import tempfile
 
     import numpy as np
@@ -124,7 +125,9 @@ def apply_impulse_response(audio: AudioT, ir: ImpulseResponseData) -> AudioT:
     except Exception as e:
         raise SonusAIError(f'Error applying IR: {e}')
 
+    path = Path(temp.name)
     temp.close()
+    path.unlink()
 
     # Reset level to previous max value
     tfm = Transformer()

sonusai/mkwav.py

@@ -72,7 +72,7 @@ def _process_mixture(mixid: int) -> None:
 
     from sonusai.mixture import mixture_metadata
     from sonusai.utils import float_to_int16
-    from sonusai.utils import write_wav
+    from sonusai.utils import write_audio
 
     mixture_filename = join(MP_GLOBAL.mixdb.location, MP_GLOBAL.mixdb.mixtures[mixid].name)
     mixture_basename = splitext(mixture_filename)[0]
@@ -100,11 +100,11 @@ def _process_mixture(mixid: int) -> None:
             if MP_GLOBAL.write_noise:
                 noise = np.array(f['noise'])
 
-    write_wav(name=mixture_basename + '_mixture.wav', audio=float_to_int16(mixture))
+    write_audio(name=mixture_basename + '_mixture.wav', audio=float_to_int16(mixture))
     if MP_GLOBAL.write_target:
-        write_wav(name=mixture_basename + '_target.wav', audio=float_to_int16(target))
+        write_audio(name=mixture_basename + '_target.wav', audio=float_to_int16(target))
     if MP_GLOBAL.write_noise:
-        write_wav(name=mixture_basename + '_noise.wav', audio=float_to_int16(noise))
+        write_audio(name=mixture_basename + '_noise.wav', audio=float_to_int16(noise))
 
     with open(file=mixture_basename + '.txt', mode='w') as f:
         f.write(mixture_metadata(MP_GLOBAL.mixdb, MP_GLOBAL.mixdb.mixture(mixid)))

sonusai/onnx_predict.py

@@ -100,7 +100,7 @@ def main() -> None:
     from sonusai.utils import create_ts_name
     from sonusai.utils import load_ort_session
     from sonusai.utils import reshape_inputs
-    from sonusai.utils import write_wav
+    from sonusai.utils import write_audio
 
     mixdb_path = None
     mixdb = None
@@ -201,7 +201,7 @@ def main() -> None:
                 predict = np.transpose(predict, [1, 0, 2])
                 predict_audio = get_audio_from_feature(feature=predict, feature_mode=feature_mode)
                 owav_name = splitext(output_fname)[0] + '_predict.wav'
-                write_wav(owav_name, predict_audio)
+                write_audio(owav_name, predict_audio)
 
 
 if __name__ == '__main__':

sonusai/post_spenh_targetf.py

@@ -137,7 +137,7 @@ def _process(file: str) -> None:
     from sonusai.mixture import get_audio_from_transform
     from sonusai.utils import float_to_int16
     from sonusai.utils import unstack_complex
-    from sonusai.utils import write_wav
+    from sonusai.utils import write_audio
 
     try:
         with h5py.File(file, 'r') as f:
@@ -153,7 +153,7 @@ def _process(file: str) -> None:
                                                                          bin_end=MP_GLOBAL.bin_end,
                                                                          ttype=MP_GLOBAL.ttype,
                                                                          gain=np.float32(1)))
-    write_wav(name=output_name, audio=float_to_int16(audio))
+    write_audio(name=output_name, audio=float_to_int16(audio))
 
 
 if __name__ == '__main__':

sonusai/speech/{voxceleb2.py → voxceleb.py}

@@ -16,14 +16,30 @@ def load_speakers(input_dir: Path) -> dict:
     import csv
 
     speakers = {}
+
+    # VoxCeleb1
+    first = True
+    with open(input_dir / 'vox1_meta.csv', newline='') as file:
+        data = csv.reader(file, delimiter='\t')
+        for row in data:
+            if first:
+                first = False
+            else:
+                speakers[row[0].strip()] = {'gender':   row[2].strip(),
+                                            'dialect':  row[3].strip(),
+                                            'category': row[4].strip()}
+
+    # VoxCeleb2
     first = True
-    with open(input_dir / 'vox2_meta_cleansed.csv', newline='') as file:
-        data = csv.reader(file)
+    with open(input_dir / 'vox2_meta.csv', newline='') as file:
+        data = csv.reader(file, delimiter='\t')
         for row in data:
             if first:
                 first = False
             else:
-                speakers[row[0].strip()] = {'gender': row[2].strip(), 'category': row[3].strip()}
+                speakers[row[1].strip()] = {'gender':   row[3].strip(),
+                                            'category': row[4].strip()}
+
     return speakers
 
 

sonusai/utils/__init__.py

@@ -49,5 +49,5 @@ from .stacked_complex import stacked_complex_imag
 from .stacked_complex import stacked_complex_real
 from .stacked_complex import unstack_complex
 from .stratified_shuffle_split import stratified_shuffle_split_mixid
-from .wave import write_wav
+from .write_audio import write_audio
 from .yes_or_no import yes_or_no

sonusai/utils/asr_functions/aaware_whisper.py

@@ -13,7 +13,7 @@ def aaware_whisper(data: ASRData) -> ASRResult:
     from sonusai import SonusAIError
     from sonusai.utils import ASRResult
     from sonusai.utils import float_to_int16
-    from sonusai.utils import write_wav
+    from sonusai.utils import write_audio
 
     url = getenv('AAWARE_WHISPER_URL')
     if url is None:
@@ -22,7 +22,7 @@ def aaware_whisper(data: ASRData) -> ASRResult:
 
     with tempfile.TemporaryDirectory() as tmp:
         file = join(tmp, 'asr.wav')
-        write_wav(name=file, audio=float_to_int16(data.audio))
+        write_audio(name=file, audio=float_to_int16(data.audio))
 
         files = {'audio_file': (file, open(file, 'rb'), 'audio/wav')}
 

sonusai/utils/{wave.py → write_audio.py}

@@ -2,8 +2,8 @@ from sonusai.mixture.constants import SAMPLE_RATE
 from sonusai.mixture.datatypes import AudioT
 
 
-def write_wav(name: str, audio: AudioT, sample_rate: int = SAMPLE_RATE) -> None:
-    """ Write a simple, uncompressed WAV file.
+def write_audio(name: str, audio: AudioT, sample_rate: int = SAMPLE_RATE) -> None:
+    """ Write an audio file.
 
     To write multiple channels, use a 2D array of shape [channels, samples].
     The bits per sample and PCM/float are determined by the data type.

{sonusai-0.17.2.dist-info → sonusai-0.17.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sonusai
-Version: 0.17.2
+Version: 0.17.3
 Summary: Framework for building deep neural network models for sound, speech, and voice AI
 Home-page: https://aaware.com
 License: GPL-3.0-only
@@ -21,6 +21,7 @@ Requires-Dist: h5py (>=3.11.0,<4.0.0)
 Requires-Dist: jiwer (>=3.0.3,<4.0.0)
 Requires-Dist: librosa (>=0.10.1,<0.11.0)
 Requires-Dist: matplotlib (>=3.8.0,<4.0.0)
+Requires-Dist: numpy (>=1.26.4,<2.0.0)
 Requires-Dist: onnx (>=1.14.1,<2.0.0)
 Requires-Dist: onnxruntime (>=1.16.1,<2.0.0)
 Requires-Dist: paho-mqtt (>=2.0.0,<3.0.0)

{sonusai-0.17.2.dist-info → sonusai-0.17.3.dist-info}/RECORD

@@ -1,7 +1,7 @@
 sonusai/__init__.py,sha256=vzTFfRB-NeO-Sm3puySDJOybk3ND_Oj6w0EejQPmH1U,2978
 sonusai/aawscd_probwrite.py,sha256=GukR5owp_0A3DrqSl9fHWULYgclNft4D5OkHIwfxxkc,3698
-sonusai/audiofe.py,sha256=AHXV7fQKumkwUSbOS-ZU6Cp1VF88DRtqt7foVbf-Nh8,11148
-sonusai/calc_metric_spenh.py,sha256=Xgy9EKbZRPAydjTZbpZjaqLBNkjQPjDmSbfL8PbVSgY,62157
+sonusai/audiofe.py,sha256=zOySiYs5ZZm60eMbA7RjhG6C0Ouhaii3WfL1d0Q8rxg,11154
+sonusai/calc_metric_spenh.py,sha256=0UvJibVjjoHTty3QFh0qzugXe-LvIj2XsMwoaIR44BM,62171
 sonusai/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sonusai/data/genmixdb.yml,sha256=-XSs_hUR6wHJVoTPmSewzXL7u61X-xmHY46lNPatxSE,1025
 sonusai/data/speech_ma01_01.wav,sha256=PK0vMKg-NR6rPE3KouxHGF6PKXnJCr7AwjMqfu98LUA,76644
@@ -41,10 +41,10 @@ sonusai/mixture/generation.py,sha256=miUrc3QOSUNIG6mDkiMCZ6M2ulivUZxlYUAJUOVomWc
 sonusai/mixture/helpers.py,sha256=GSGSD2KnvOeEIB6IwNTxyaQNjghTSBMB729kUEd_RiM,22403
 sonusai/mixture/log_duration_and_sizes.py,sha256=baTUpqyM15wA125jo9E3posmVJUe3WlpksyO6v9Jul0,1347
 sonusai/mixture/mapped_snr_f.py,sha256=mlbYM1t14OXe_Zg4CjpWTuA_Zun4W0O3bSUXeodRBQs,1845
-sonusai/mixture/mixdb.py,sha256=PvLeEOLn2n0EfBRe7GuvUQfOmj3SKOrzjUimw2qRHP8,49792
+sonusai/mixture/mixdb.py,sha256=zfBaVOuMKHTDzmwR4hWRpGxFwnV_fJkwLDmn9M1SDds,49791
 sonusai/mixture/soundfile_audio.py,sha256=mHa5SIXsu_uE0j3DO52GydRJrvWSzU_nII-7YJfQ6Qo,4154
 sonusai/mixture/sox_audio.py,sha256=HT3kYA9TP5QPCuoOJdUMnGVN-qY6q96DGL8zxuog76o,12277
-sonusai/mixture/sox_augmentation.py,sha256=F9tBdNvX2guCn7gRppAFrxRnBtjw9q6qAq2_v_A4hh0,4490
+sonusai/mixture/sox_augmentation.py,sha256=kBWPrsFk0EBi71nLcKt5v0GA34bY7g9D9x0cEamNWbU,4564
 sonusai/mixture/speaker_metadata.py,sha256=l98avdxLYUsSDZ88xUjfvHnACkbnD0_Dg1aBGDbzS9I,1380
 sonusai/mixture/spectral_mask.py,sha256=8AkCwhy-PSdP1Uri9miKZP-bXFYnFcH_c9xZCGrHavU,2071
 sonusai/mixture/target_class_balancing.py,sha256=NTNiKZH0_PWLooeow0l41CjJKK8ZTMVbUqz9ZkaNtWk,4900
@@ -62,10 +62,10 @@ sonusai/mixture/truth_functions/phoneme.py,sha256=stYdlPuNytQK_LLT61OJLfYSqKd-sD
 sonusai/mixture/truth_functions/sed.py,sha256=8cHjEFjZaH_0hIOHhPmj4AJz2GpEADM6Ys2x4NoiWSY,2469
 sonusai/mixture/truth_functions/target.py,sha256=KAsjugDRooOA5BRcHVAbZRgV7l8S5CFg7CZ0XtKZaQ0,5764
 sonusai/mkmanifest.py,sha256=imI8swwPYVzumrUYEL-9JLvun-ez98PtlUBj2b729k8,8682
-sonusai/mkwav.py,sha256=kLfC2ZuF-t8P97nqYw2falTZpymxAeXv0YTJCe6nK10,5356
-sonusai/onnx_predict.py,sha256=ZhicNEbjxm34edIrUcmuvKkV3NRFQk4LBn1LUCFdPjg,8733
+sonusai/mkwav.py,sha256=zfSyIiQTIK3KV9Ij33jkLhhZIMVYqaROcRQ4S7c4sIo,5364
+sonusai/onnx_predict.py,sha256=jSxhD2oFyGSTHOGCXbW4fRT-k4SqKOboK2JaDO-yWcs,8737
 sonusai/plot.py,sha256=ERkmxMM3qjcCDm4LGDQY4fRAncCYAzP7uW8iZ7_brcg,17105
-sonusai/post_spenh_targetf.py,sha256=xOz5T6WZuyTHmfbtILIY9skgH064Wvi2GF2Bo5L3YMU,4998
+sonusai/post_spenh_targetf.py,sha256=pHaJZtms7aj4r6sgqQnEGVi6Gg8H_V29szigogV1vZ8,5002
 sonusai/queries/__init__.py,sha256=oKY5JeqZ4Cz7DwCwPc1_ydB8bUs6KaMcWFp_w02TjOs,255
 sonusai/queries/queries.py,sha256=oV-m9uiLZOwYTK-Wo7Gf8dpGisaoGf6uDsAJAarVqZI,7553
 sonusai/speech/__init__.py,sha256=SuPcU_K9wQISsZRIzsRNLtEC6cb616l-Jlx3PU-HWMs,113
@@ -76,14 +76,14 @@ sonusai/speech/textgrid.py,sha256=8hB6SdEEXxo6JXVFq8mJ1-ilRbBiRXhaHTQjA-HWg-0,33
 sonusai/speech/timit.py,sha256=1vWgj6isD3ATOjMJSTjOPLmDkYyB65M5MwYipEmLEvg,4081
 sonusai/speech/types.py,sha256=4eKVPAktpkIrZ2qoVp2iT45zxTVNocQEGT6O_Zlub_w,214
 sonusai/speech/vctk.py,sha256=EAMEBAzjZUI6dw15n-yI2oCN-H4tzM9t4aUVlOxpAbo,1540
-sonusai/speech/voxceleb2.py,sha256=-u0mtxFm4chFipLgMGZXR5EBDtYTCQoU1_j_wYTGwPY,2158
+sonusai/speech/voxceleb.py,sha256=aJGN0yDb2LFLmCKmRzmUEjpZWQ-QGWw6XWOpy9967AI,2686
 sonusai/summarize_metric_spenh.py,sha256=OiZe_bhCq5esXNhsOkHDD7g4ssYrpENDHvDVoPzV9iw,1822
 sonusai/tplot.py,sha256=85T6OPZfxVegHBiSuilFpdgCNMEE0VKAuciNy4rCY5Y,14544
-sonusai/utils/__init__.py,sha256=y2Xe72QMNk8LbbjdOUOHiR5eVg32fYrFhinWSuSHi-w,2248
+sonusai/utils/__init__.py,sha256=h7QrOyEBMUMoIBFKZpNwDG8Jg-1uw3bs-qflB3CXxhU,2257
 sonusai/utils/asl_p56.py,sha256=-bvQpd-jRQVURbkZJpRoyEAq6gTv9Rc3oFDbh5_lcjY,3861
 sonusai/utils/asr.py,sha256=6y6VYJizHpuQ3MgKbEQ4t2gofO-MW6Ez23oAd6d23IE,2920
 sonusai/utils/asr_functions/__init__.py,sha256=JyHK67s97bw7QzrlkboWhws4yNytdPatqzLJxfwx-yw,43
-sonusai/utils/asr_functions/aaware_whisper.py,sha256=LzO9CZV0wBWkjmCR2nSWN_AW9UJwriAsC1OYSlfVeT8,1981
+sonusai/utils/asr_functions/aaware_whisper.py,sha256=Ew3zb8OfbxEW7q1s-KA7D5eph4SjVSUAJgiLK-vVqhI,1985
 sonusai/utils/asr_manifest_functions/__init__.py,sha256=jfi9xC5c86F_aMSsI5Xj-pxWGxuQ7fwZ8Wdf4T7kDsA,343
 sonusai/utils/asr_manifest_functions/data.py,sha256=nO4oT3EQmydwn1pzc-ZM09yz4X2ic-LQuHzGEnJhKe8,32
 sonusai/utils/asr_manifest_functions/librispeech.py,sha256=_3tGc8qfAUpYJZ0_avpW0vGp7zjdpeqj1HAgXi3TL4Q,1612
@@ -118,10 +118,10 @@ sonusai/utils/reshape.py,sha256=E8Eu6grynaeWwVO6peIR0BF22SrVaJSa1Rkl109lq6Y,5997
 sonusai/utils/seconds_to_hms.py,sha256=oxLuZhTJJr9swj-fOSOrZJ5vBNM7_BrOMQhX1pYpiv0,260
 sonusai/utils/stacked_complex.py,sha256=feLhz3GC1ILxBGMHOj3sJK--sidsXKbfwkalwAVwizc,2950
 sonusai/utils/stratified_shuffle_split.py,sha256=rJNXvBp-GxoKzH3OpL7k0ANSu5xMP2zJ7K1fm_33UzE,7022
-sonusai/utils/wave.py,sha256=O4ZXkZ6wjrKGa99wBCdFd8G6bp91MXXDnmGihpaEMh0,856
+sonusai/utils/write_audio.py,sha256=ZsPGExwM86QHLLN2LOWekK2uAqf5pV_1oRW811p0QAI,840
 sonusai/utils/yes_or_no.py,sha256=eMLXBVH0cEahiXY4W2KNORmwNQ-ba10eRtldh0y4NYg,263
 sonusai/vars.py,sha256=m2AefF0m5bXWGXpJj8Pi42zWL2ydeEj7bkak3GrtMyM,940
-sonusai-0.17.2.dist-info/METADATA,sha256=eZmrmMohaVLBAz3v2lGdBcwGCjnszgDiKcAHI9i_2YE,2483
-sonusai-0.17.2.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-sonusai-0.17.2.dist-info/entry_points.txt,sha256=zMNjEphEPO6B3cD1GNpit7z-yA9tUU5-j3W2v-UWstU,92
-sonusai-0.17.2.dist-info/RECORD,,
+sonusai-0.17.3.dist-info/METADATA,sha256=Zu3DK9fCT1xiipWOBY4JhUZJ3qm1cVRc5eLAXonDb2s,2522
+sonusai-0.17.3.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+sonusai-0.17.3.dist-info/entry_points.txt,sha256=zMNjEphEPO6B3cD1GNpit7z-yA9tUU5-j3W2v-UWstU,92
+sonusai-0.17.3.dist-info/RECORD,,