[pull] main from m-bain:main

README.md

@@ -144,7 +144,7 @@ To label the transcript with speaker ID's (set number of speakers if known e.g.
 
 To run on CPU instead of GPU (and for running on Mac OS X):
 
-    whisperx path/to/audio.wav --compute_type int8
+    whisperx path/to/audio.wav --compute_type int8 --device cpu
 
 ### Other languages
 
@@ -166,6 +166,7 @@ See more examples in other languages [here](EXAMPLES.md).
 ```python
 import whisperx
 import gc
+from whisperx.diarize import DiarizationPipeline
 
 device = "cuda"
 audio_file = "audio.mp3"
@@ -196,7 +197,7 @@ print(result["segments"]) # after alignment
 # import gc; import torch; gc.collect(); torch.cuda.empty_cache(); del model_a
 
 # 3. Assign speaker labels
-diarize_model = whisperx.diarize.DiarizationPipeline(use_auth_token=YOUR_HF_TOKEN, device=device)
+diarize_model = DiarizationPipeline(use_auth_token=YOUR_HF_TOKEN, device=device)
 
 # add min/max number of speakers if known
 diarize_segments = diarize_model(audio)

whisperx/asr.py

@@ -319,7 +319,8 @@ def load_model(
         whisper_arch - The name of the Whisper model to load.
         device - The device to load the model on.
         compute_type - The compute type to use for the model.
-        vad_method - The vad method to use. vad_model has higher priority if is not None.
+        vad_model - The vad model to manually assign.
+        vad_method - The vad method to use. vad_model has a higher priority if it is not None.
         options - A dictionary of options to use for the model.
         language - The language of the model. (use English for now)
         model - The WhisperModel instance to use.

whisperx/transcribe.py

@@ -119,7 +119,6 @@ def transcribe_task(args: dict, parser: argparse.ArgumentParser):
 
     # Part 1: VAD & ASR Loop
     results = []
-    tmp_results = []
     # model = load_model(model_name, device=device, download_root=model_dir)
     model = load_model(
         model_name,