- # Decoder
-
- f.DEFINE_boolean('utf8', False, 'enable UTF-8 mode. When this is used the model outputs UTF-8 sequences directly rather than using an alphabet mapping.')
- f.DEFINE_string('alphabet_config_path', 'data/alphabet.txt', 'path to the configuration file specifying the alphabet used by the network. See the comment in data/alphabet.txt for a description of the format.')
- f.DEFINE_string('scorer_path', 'data/lm/kenlm.scorer', 'path to the external scorer file.')
- f.DEFINE_alias('scorer', 'scorer_path')
- f.DEFINE_integer('beam_width', 1024, 'beam width used in the CTC decoder when building candidate transcriptions')
- f.DEFINE_float('lm_alpha', 0.931289039105002, 'the alpha hyperparameter of the CTC decoder. Language Model weight.')
- f.DEFINE_float('lm_beta', 1.1834137581510284, 'the beta hyperparameter of the CTC decoder. Word insertion weight.')
- f.DEFINE_float('cutoff_prob', 1.0, 'only consider characters until this probability mass is reached. 1.0 = disabled.')
- f.DEFINE_integer('cutoff_top_n', 300, 'only process this number of characters sorted by probability mass for each time step. If bigger than alphabet size, disabled.')
-
- # Inference mode
-
- f.DEFINE_string('one_shot_infer', '', 'one-shot inference mode: specify a wav file and the script will load the checkpoint and perform inference on it.')
-
- # Optimizer mode
-
- f.DEFINE_float('lm_alpha_max', 5, 'the maximum of the alpha hyperparameter of the CTC decoder explored during hyperparameter optimization. Language Model weight.')
- f.DEFINE_float('lm_beta_max', 5, 'the maximum beta hyperparameter of the CTC decoder explored during hyperparameter optimization. Word insertion weight.')
- f.DEFINE_integer('n_trials', 2400, 'the number of trials to run during hyperparameter optimization.')