Merge branch 'develop' into develop

CHANGELOG.md

@@ -2,18 +2,37 @@
 
 ## develop
 
+### Fixes
+
+- fix: fix support for `numpy==2.x` ([@ibevers](https://github.com/ibevers/))
+
+## Version 3.3.0 (2024-06-14)
+
+### TL;DR
+
+`pyannote.audio` does [speech separation](https://hf.co/pyannote/speech-separation-ami-1.0): multi-speaker audio in, one audio channel per speaker out!
+
+```bash
+pip install pyannote.audio[separation]==3.3.0
+```
+
 ### New features
 
+- feat(task): add `PixIT` joint speaker diarization and speech separation task (with [@joonaskalda](https://github.com/joonaskalda/))
+- feat(model): add `ToTaToNet` joint speaker diarization and speech separation model (with [@joonaskalda](https://github.com/joonaskalda/))
+- feat(pipeline): add `SpeechSeparation` pipeline (with [@joonaskalda](https://github.com/joonaskalda/))
 - feat(io): add option to select torchaudio `backend`
 
 ### Fixes
 
 - fix(task): fix wrong train/development split when training with (some) meta-protocols ([#1709](https://github.com/pyannote/pyannote-audio/issues/1709))
+- fix(task): fix metadata preparation with missing validation subset ([@clement-pages](https://github.com/clement-pages/))
 
 ### Improvements
 
 - improve(io): when available, default to using `soundfile` backend
 - improve(pipeline): do not extract embeddings when `max_speakers` is set to 1
+- improve(pipeline): optimize memory usage of most pipelines ([#1713](https://github.com/pyannote/pyannote-audio/pull/1713) by [@benniekiss](https://github.com/benniekiss/))
 
 ## Version 3.2.0 (2024-05-08)
 

pyannote/audio/core/inference.py

@@ -526,7 +526,7 @@ def aggregate(
         warm_up: Tuple[float, float] = (0.0, 0.0),
         epsilon: float = 1e-12,
         hamming: bool = False,
-        missing: float = np.NaN,
+        missing: float = np.nan,
         skip_average: bool = False,
     ) -> SlidingWindowFeature:
         """Aggregation
@@ -559,9 +559,6 @@ def aggregate(
             step=frames.step,
         )
 
-        masks = 1 - np.isnan(scores)
-        scores.data = np.nan_to_num(scores.data, copy=True, nan=0.0)
-
         # Hamming window used for overlap-add aggregation
         hamming_window = (
             np.hamming(num_frames_per_chunk).reshape(-1, 1)
@@ -613,11 +610,13 @@ def aggregate(
         )
 
         # loop on the scores of sliding chunks
-        for (chunk, score), (_, mask) in zip(scores, masks):
+        for chunk, score in scores:
             # chunk ~ Segment
             # score ~ (num_frames_per_chunk, num_classes)-shaped np.ndarray
             # mask ~ (num_frames_per_chunk, num_classes)-shaped np.ndarray
-
+            mask = 1 - np.isnan(score)
+            np.nan_to_num(score, copy=False, nan=0.0)
+
             start_frame = frames.closest_frame(chunk.start + 0.5 * frames.duration)
 
             aggregated_output[start_frame : start_frame + num_frames_per_chunk] += (

pyannote/audio/core/task.py

@@ -595,7 +595,9 @@ def prepare_data(self):
         prepared_data["metadata-labels"] = np.array(unique_labels, dtype=np.str_)
         unique_labels.clear()
 
-        self.prepare_validation(prepared_data)
+        if self.has_validation:
+            self.prepare_validation(prepared_data)
+
         self.post_prepare_data(prepared_data)
 
         # save prepared data on the disk