turn off inference

it doesnt work when you have a generation config and there is no documentation about this

README.md

@@ -55,14 +55,7 @@ widget:
     interested and anyone basical e may be applyind reaching the browing
     approach were
 - medical course audio transcription
-inference:
-  parameters:
-    max_length: 128
-    min_length: 4
-    num_beams: 4
-    repetition_penalty: 1.21
-    length_penalty: 1
-    early_stopping: true
+inference: False
 pipeline_tag: text2text-generation
 language:
 - en