Update README.md

README.md

@@ -137,6 +137,27 @@ print(result)
 +     return_unique_speaker=False
 ```
 
+- To contorol the number of speakers (see [here](https://huggingface.co/pyannote/speaker-diarization-3.1#controlling-the-number-of-speakers)):
+```diff
+result = pipe(
+     "sample_diarization_japanese.mp3",
++    num_speakers=2,
+     add_punctuation=False,
+     return_unique_speaker=True,
+     generate_kwargs=generate_kwargs
+)
+```
+or
+```diff
+result = pipe(
+     "sample_diarization_japanese.mp3",
++    min_speakers=2,
++    max_speakers=5,
+     add_punctuation=False,
+     return_unique_speaker=True,
+     generate_kwargs=generate_kwargs
+)
+```
 
 ### Flash Attention 2
 We recommend using [Flash-Attention 2](https://huggingface.co/docs/transformers/main/en/perf_infer_gpu_one#flashattention-2)