sonusai 0.18.4__py3-none-any.whl → 0.18.6__py3-none-any.whl

sonusai/mixture/mixdb.py

@@ -1063,25 +1063,22 @@ class MixtureDatabase:
         if is_textgrid:
             for target in self.mixture(mixid).targets:
                 data = get_textgrid_tier_from_target_file(self.target_file(target.file_id).name, tier)
-                if data is not None:
-                    if isinstance(data, list):
-                        # Check for tempo augmentation and adjust Interval start and end data as needed
-                        entries = []
-                        for entry in data:
-                            if target.augmentation.tempo is not None:
-                                entries.append(Interval(entry.start / target.augmentation.tempo,
-                                                        entry.end / target.augmentation.tempo,
-                                                        entry.label))
-                            else:
-                                entries.append(entry)
-                        results.append(entries)
-                    else:
-                        results.append(data)
+                if isinstance(data, list):
+                    # Check for tempo augmentation and adjust Interval start and end data as needed
+                    entries = []
+                    for entry in data:
+                        if target.augmentation.tempo is not None:
+                            entries.append(Interval(entry.start / target.augmentation.tempo,
+                                                    entry.end / target.augmentation.tempo,
+                                                    entry.label))
+                        else:
+                            entries.append(entry)
+                    results.append(entries)
+                else:
+                    results.append(data)
         else:
             for target in self.mixture(mixid).targets:
-                data = self.speaker(self.target_file(target.file_id).speaker_id, tier)
-                if data is not None:
-                    results.append(data)
+                results.append(self.speaker(self.target_file(target.file_id).speaker_id, tier))
 
         return sorted(results)
 
@@ -1265,23 +1262,25 @@ class MixtureDatabase:
             # Otherwise, generate data as needed
             if m.startswith('mxwer'):
                 parts = m.split('.')
-                if len(parts) != 3:
+                if len(parts) != 2:
                     raise SonusAIError(
-                        f"Unrecognized 'mwwer' format: '{m}'; must be of the form: 'mxwer.<engine>.<model>'")
-                asr_engine = parts[1]
-                asr_model = parts[2]
+                        f"Unrecognized 'mxwer' format: '{m}'; must be of the form: 'mxwer.<name>'")
+                asr_name = parts[1]
+                asr_config = self.asr_configs.get(asr_name, None)
+                if asr_config is None:
+                    raise SonusAIError(f"Unrecognized metric: '{m}'")
 
-                if asr_engine == 'none' or self.mixture(m_id).snr < -96:
+                if self.mixture(m_id).snr < -96:
                     # noise only, ignore/reset target asr
                     return float('nan')
 
                 # ignore mixup
                 target_asr = self.mixture_speech_metadata(m_id, 'text')[0]
                 if target_asr is None:
-                    target_asr = calc_asr(target_audio(), engine=asr_engine, whisper_model_name=asr_model).text
+                    target_asr = calc_asr(target_audio(), **asr_config).text
 
                 if target_asr:
-                    mixture_asr = calc_asr(mixture_audio(), engine=asr_engine, whisper_model_name=asr_model).text
+                    mixture_asr = calc_asr(mixture_audio(), **asr_config).text
                     return calc_wer(mixture_asr, target_asr).wer * 100
 
                 # TODO: should this be NaN like above?

{sonusai-0.18.4.dist-info → sonusai-0.18.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sonusai
-Version: 0.18.4
+Version: 0.18.6
 Summary: Framework for building deep neural network models for sound, speech, and voice AI
 Home-page: https://aaware.com
 License: GPL-3.0-only

{sonusai-0.18.4.dist-info → sonusai-0.18.6.dist-info}/RECORD

@@ -46,7 +46,7 @@ sonusai/mixture/feature.py,sha256=Rwuf82IoXzhHPGbKYVGcatImF_ssBf_FfvbqghVPXtg,41
 sonusai/mixture/generation.py,sha256=W3n6ipI-dxg4Wj6YBJn8RTpFqkAyIXzxwObeFbSLq08,42801
 sonusai/mixture/helpers.py,sha256=eC9ZysEa-83VLKen_9PKWzr8w9dkHj4lp6rMB2fNLbg,24759
 sonusai/mixture/log_duration_and_sizes.py,sha256=baTUpqyM15wA125jo9E3posmVJUe3WlpksyO6v9Jul0,1347
-sonusai/mixture/mixdb.py,sha256=dtEuF2S4wg8G5pl_lkfly5k0kAg_g9xMukVLdb4G8iY,57458
+sonusai/mixture/mixdb.py,sha256=WPXuziS0SePtKkd7qtkE7Db8rV-TKQoUBvs4GPieTek,57332
 sonusai/mixture/soundfile_audio.py,sha256=BwO4lftNvrhoPTJERONcrpxSpM2fjO6kL_e5Ylz742A,4220
 sonusai/mixture/sox_audio.py,sha256=Pu5RLE8lKKlGOzZsbfcVzbDvy7YPGBuGpbD_PxowFqA,12511
 sonusai/mixture/sox_augmentation.py,sha256=kBWPrsFk0EBi71nLcKt5v0GA34bY7g9D9x0cEamNWbU,4564
@@ -119,7 +119,7 @@ sonusai/utils/stratified_shuffle_split.py,sha256=rJNXvBp-GxoKzH3OpL7k0ANSu5xMP2z
 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-0.18.4.dist-info/METADATA,sha256=8Q0ANLLD6sjL_HJgqY3rrAEyj6m2emeOgPeraSjnUZ4,2591
-sonusai-0.18.4.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-sonusai-0.18.4.dist-info/entry_points.txt,sha256=zMNjEphEPO6B3cD1GNpit7z-yA9tUU5-j3W2v-UWstU,92
-sonusai-0.18.4.dist-info/RECORD,,
+sonusai-0.18.6.dist-info/METADATA,sha256=L4wl__zTyqiH1SEMDPIIJcgLM7Uxqa6lQ9EMXVjXRlI,2591
+sonusai-0.18.6.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+sonusai-0.18.6.dist-info/entry_points.txt,sha256=zMNjEphEPO6B3cD1GNpit7z-yA9tUU5-j3W2v-UWstU,92
+sonusai-0.18.6.dist-info/RECORD,,