add description for model options

README.md

@@ -8,13 +8,13 @@ Model trained in 8-bit with LoRA
 
 Usage:
 
-prepare pipeline:
+prepare pipeline, setting to default generate_opts will give you (deterministic) greedy decoding with up to 112 tokens generated, no repetition penalty:
 ```
 asr_model=prepare_pipeline(
         model_dir='.', # wherever you save the model
         generate_opts={'max_new_tokens':112,
                 'num_beams':1,
-                'repetition_penalty':r1,
+                'repetition_penalty':1,
                 'do_sample':False
                             }
                 )