default diarization backend in now sortformer

README.md

@@ -186,7 +186,7 @@ The package includes an HTML/JavaScript implementation [here](https://github.com
 | Diarization options | Description | Default |
 |-----------|-------------|---------|
 | `--diarization` | Enable speaker identification | `False` |
-| `--diarization-backend` |  `diart` or `sortformer` | `diart` |
+| `--diarization-backend` |  `diart` or `sortformer` | `sortformer` |
 | `--punctuation-split` | Use punctuation to improve speaker boundaries | `True` |
 | `--segmentation-model` | Hugging Face model ID for Diart segmentation model. [Available models](https://github.com/juanmc2005/diart/tree/main?tab=readme-ov-file#pre-trained-models) | `pyannote/segmentation-3.0` |
 | `--embedding-model` | Hugging Face model ID for Diart embedding model. [Available models](https://github.com/juanmc2005/diart/tree/main?tab=readme-ov-file#pre-trained-models) | `speechbrain/spkrec-ecapa-voxceleb` |

whisperlivekit/core.py

@@ -57,7 +57,7 @@ class TranscriptionEngine:
             "static_init_prompt": None,
             "max_context_tokens": None,
             "model_path": './base.pt',
-            "diarization_backend": "diart",
+            "diarization_backend": "sortformer",
             # diart params:
             "segmentation_model": "pyannote/segmentation-3.0",
             "embedding_model": "pyannote/embedding",

whisperlivekit/parse_args.py

@@ -61,7 +61,7 @@ def parse_args():
     parser.add_argument(
         "--diarization-backend",
         type=str,
-        default="diart",
+        default="sortformer",
         choices=["sortformer", "diart"],
         help="The diarization backend to use.",
     )