diff --git a/STT/whisper_stt_handler.py b/STT/whisper_stt_handler.py index ea37b8ba2aa86cac52534a7e843d9d2705270cfd..b1596a9b701cbed35640e69989bca15fd6639e39 100644 --- a/STT/whisper_stt_handler.py +++ b/STT/whisper_stt_handler.py @@ -67,7 +67,7 @@ class WhisperSTTHandler(BaseHandler): # generating more tokens than previously will trigger CUDA graphs capture # one should warmup with a number of generated tokens above max tokens targeted for subsequent generation warmup_gen_kwargs = { - "min_new_tokens": self.gen_kwargs["min_new_tokens"], + "min_new_tokens": self.gen_kwargs["max_new_tokens"], # Yes, assign max_new_tokens to min_new_tokens "max_new_tokens": self.gen_kwargs["max_new_tokens"], **self.gen_kwargs, } diff --git a/arguments_classes/whisper_stt_arguments.py b/arguments_classes/whisper_stt_arguments.py index 2edb4c24e7d75bd8a204edf1a82a8dd79b0df457..bed382dda754da36965b4d86e68a7f8b4d9c322c 100644 --- a/arguments_classes/whisper_stt_arguments.py +++ b/arguments_classes/whisper_stt_arguments.py @@ -33,12 +33,6 @@ class WhisperSTTHandlerArguments: "help": "The maximum number of new tokens to generate. Default is 128." }, ) - stt_gen_min_new_tokens: int = field( - default=0, - metadata={ - "help": "The minimum number of new tokens to generate. Default is 0." - }, - ) stt_gen_num_beams: int = field( default=1, metadata={