Merge pull request #527 from jkukul/pass-beam-size-to-fast-whisper

This commit is contained in:
Max Bain
2023-10-15 07:15:13 -07:00
committed by GitHub
2 changed files with 3 additions and 1 deletions

View File

@ -145,6 +145,8 @@ class WhisperModel(faster_whisper.WhisperModel):
result = self.model.generate(
encoder_output,
[prompt] * batch_size,
beam_size=options.beam_size,
patience=options.patience,
length_penalty=options.length_penalty,
max_length=self.max_length,
suppress_blank=options.suppress_blank,

View File

@ -51,7 +51,7 @@ def cli():
parser.add_argument("--temperature", type=float, default=0, help="temperature to use for sampling")
parser.add_argument("--best_of", type=optional_int, default=5, help="number of candidates when sampling with non-zero temperature")
parser.add_argument("--beam_size", type=optional_int, default=5, help="number of beams in beam search, only applicable when temperature is zero")
parser.add_argument("--patience", type=float, default=None, help="optional patience value to use in beam decoding, as in https://arxiv.org/abs/2204.05424, the default (1.0) is equivalent to conventional beam search")
parser.add_argument("--patience", type=float, default=1.0, help="optional patience value to use in beam decoding, as in https://arxiv.org/abs/2204.05424, the default (1.0) is equivalent to conventional beam search")
parser.add_argument("--length_penalty", type=float, default=1.0, help="optional token length penalty coefficient (alpha) as in https://arxiv.org/abs/1609.08144, uses simple length normalization by default")
parser.add_argument("--suppress_tokens", type=str, default="-1", help="comma-separated list of token ids to suppress during sampling; '-1' will suppress most special characters except common punctuations")