diff --git a/README.md b/README.md
index b52401b8..a497604d 100644
--- a/README.md
+++ b/README.md
@@ -177,7 +177,7 @@ print(result["segments"]) # after alignment
 diarize_model = whisperx.DiarizationPipeline(use_auth_token=YOUR_HF_TOKEN, device=device)
 
 # add min/max number of speakers if known
-diarize_segments = diarize_model(audio_file)
+diarize_segments = diarize_model(audio)
 # diarize_model(audio_file, min_speakers=min_speakers, max_speakers=max_speakers)
 
 result = whisperx.assign_word_speakers(diarize_segments, result)
diff --git a/whisperx/diarize.py b/whisperx/diarize.py
index 320d2a48..2a9bd697 100644
--- a/whisperx/diarize.py
+++ b/whisperx/diarize.py
@@ -4,6 +4,8 @@
 from typing import Optional, Union
 import torch
 
+from .audio import SAMPLE_RATE
+
 class DiarizationPipeline:
     def __init__(
         self,
@@ -16,7 +18,11 @@ def __init__(
         self.model = Pipeline.from_pretrained(model_name, use_auth_token=use_auth_token).to(device)
 
     def __call__(self, audio, min_speakers=None, max_speakers=None):
-        segments = self.model(audio, min_speakers=min_speakers, max_speakers=max_speakers)
+        audio_data = {
+            'waveform': torch.from_numpy(audio[None, :]),
+            'sample_rate': SAMPLE_RATE
+        }
+        segments = self.model(audio_data, min_speakers=min_speakers, max_speakers=max_speakers)
         diarize_df = pd.DataFrame(segments.itertracks(yield_label=True))
         diarize_df['start'] = diarize_df[0].apply(lambda x: x.start)
         diarize_df['end'] = diarize_df[0].apply(lambda x: x.end)
diff --git a/whisperx/transcribe.py b/whisperx/transcribe.py
index 1cc144e6..be2dfaf2 100644
--- a/whisperx/transcribe.py
+++ b/whisperx/transcribe.py
@@ -202,7 +202,8 @@ def cli():
         results = []
         diarize_model = DiarizationPipeline(use_auth_token=hf_token, device=device)
         for result, input_audio_path in tmp_results:
-            diarize_segments = diarize_model(input_audio_path, min_speakers=min_speakers, max_speakers=max_speakers)
+            audio = load_audio(input_audio_path)
+            diarize_segments = diarize_model(audio, min_speakers=min_speakers, max_speakers=max_speakers)
             result = assign_word_speakers(diarize_segments, result)
             results.append((result, input_audio_path))
     # >> Write