Update README.md

README.md

@@ -32,7 +32,7 @@ pipeline_tag: automatic-speech-recognition
             input_features,
             max_new_tokens=450,  # change as needed
             return_dict_in_generate=True,
-            forced_decoder_ids=[[2, 50358], [3, 50363]],  # different forced_decoder_ids
+            forced_decoder_ids=[[2, 50358], [3, 50363]],  # forced to translate any language with no timestamps
         )
         return {"sequences": outputs["sequences"]}