Remove unused code in Vad class

* fix: improve handling of speaker embeddings in transcribe_task

* chore: bump version to 3.4.1

pyproject.toml

@@ -2,7 +2,7 @@
 urls = { repository = "https://github.com/m-bain/whisperx" }
 authors = [{ name = "Max Bain" }]
 name = "whisperx"
-version = "3.4.0"
+version = "3.4.2"
 description = "Time-Accurate Automatic Speech Recognition using Whisper."
 readme = "README.md"
 requires-python = ">=3.9, <3.13"

uv.lock

@@ -2788,7 +2788,7 @@ wheels = [
 
 [[package]]
 name = "whisperx"
-version = "3.4.0"
+version = "3.4.2"
 source = { editable = "." }
 dependencies = [
     { name = "ctranslate2" },

whisperx/alignment.py

@@ -424,7 +424,7 @@ def get_wildcard_emission(frame_emission, tokens, blank_id):
     wildcard_mask = (tokens == -1)
 
     # Get scores for non-wildcard positions
-    regular_scores = frame_emission[tokens.clamp(min=0)]  # clamp to avoid -1 index
+    regular_scores = frame_emission[tokens.clamp(min=0).long()]  # clamp to avoid -1 index
 
     # Create a mask and compute the maximum value without modifying frame_emission
     max_valid_score = frame_emission.clone()   # Create a copy

whisperx/transcribe.py

@@ -213,12 +213,19 @@ def transcribe_task(args: dict, parser: argparse.ArgumentParser):
         results = []
         diarize_model = DiarizationPipeline(model_name=diarize_model_name, use_auth_token=hf_token, device=device)
         for result, input_audio_path in tmp_results:
-            diarize_segments, speaker_embeddings = diarize_model(
+            diarize_result = diarize_model(
                 input_audio_path, 
                 min_speakers=min_speakers, 
                 max_speakers=max_speakers, 
                 return_embeddings=return_speaker_embeddings
             )
+
+            if return_speaker_embeddings:
+                diarize_segments, speaker_embeddings = diarize_result
+            else:
+                diarize_segments = diarize_result
+                speaker_embeddings = None
+
             result = assign_word_speakers(diarize_segments, result, speaker_embeddings)
             results.append((result, input_audio_path))
     # >> Write

whisperx/vads/vad.py

@@ -52,23 +52,3 @@ class Vad:
 
         return merged_segments
 
-    # Unused function
-    @staticmethod
-    def merge_vad(vad_arr, pad_onset=0.0, pad_offset=0.0, min_duration_off=0.0, min_duration_on=0.0):
-        active = Annotation()
-        for k, vad_t in enumerate(vad_arr):
-            region = Segment(vad_t[0] - pad_onset, vad_t[1] + pad_offset)
-            active[region, k] = 1
-
-        if pad_offset > 0.0 or pad_onset > 0.0 or min_duration_off > 0.0:
-            active = active.support(collar=min_duration_off)
-
-        # remove tracks shorter than min_duration_on
-        if min_duration_on > 0:
-            for segment, track in list(active.itertracks()):
-                if segment.duration < min_duration_on:
-                    del active[segment, track]
-
-        active = active.for_json()
-        active_segs = pd.DataFrame([x['segment'] for x in active['content']])
-        return active_segs