multiple decoding

README.md

@@ -63,9 +63,17 @@ Please notice that we encourage you to read our tutorials and learn more about
 from speechbrain.inference.ASR import EncoderDecoderASR
 
 asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-conformer-largescaleasr", savedir="pretrained_models/asr-conformer-largescaleasr")
+
+# For a full decoding with a large beam size (can be slow):
 asr_model.transcribe_file("speechbrain/asr-conformer-largescaleasr/example.wav")
 
+# For smaller beam size:
+asr_model.transcribe_file("speechbrain/asr-conformer-largescaleasr/example.wav", overrides={"test_beam_size":"10"})
+
+# For even faster decoding
+asr_model.transcribe_file("speechbrain/asr-conformer-largescaleasr/example.wav", overrides={"test_beam_size":"10", "ctc_weight_decode":0.0})
 ```
+
 ### Inference on GPU
 To perform inference on the GPU, add  `run_opts={"device":"cuda"}`  when calling the `from_hparams` method.