Mirroristas/whisper
2
0
Fork 0
mirror of https://github.com/openai/whisper.git synced 2025-11-24 14:35:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

add always_use_initial_prompt

Browse Source
This commit is contained in:
mercury233 2023-03-07 11:22:03 +08:00
parent 25639fc17d
commit 01768370d8
1 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
whisper/transcribe.py
View File

@ -46,6 +46,7 @@ def transcribe(
no_speech_threshold: Optional[float] = 0.6,
condition_on_previous_text: bool = True,
initial_prompt: Optional[str] = None,
always_use_initial_prompt: bool = False,
word_timestamps: bool = False,
prepend_punctuations: str = "\"'“¿([{-",
append_punctuations: str = "\"'.。,，!！?？:：”)]}、",
@ -102,6 +103,11 @@ def transcribe(
"prompt-engineer" a context for transcription, e.g. custom vocabularies or proper nouns
to make it more likely to predict those word correctly.
always_use_initial_prompt: bool
if True, the initial_prompt will be used to all windows, and condition_on_previous_text
will be ignored. Enabling this may make the text more consistent if the audio is long
and you set the initial_prompt properly.
decode_options: dict
Keyword arguments to construct `DecodingOptions` instances
@ -275,7 +281,11 @@ def transcribe(
segment_duration = segment_size * HOP_LENGTH / SAMPLE_RATE
mel_segment = pad_or_trim(mel_segment, N_FRAMES).to(model.device).to(dtype)
decode_options["prompt"] = all_tokens[prompt_reset_since:]
if always_use_initial_prompt:
decode_options["prompt"] = initial_prompt_tokens
else:
decode_options["prompt"] = all_tokens[prompt_reset_since:]
result: DecodingResult = decode_with_fallback(mel_segment)
tokens = torch.tensor(result.tokens)
@ -530,6 +540,7 @@ def cli():
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")
parser.add_argument("--initial_prompt", type=str, default=None, help="optional text to provide as a prompt for the first window.")
parser.add_argument("--condition_on_previous_text", type=str2bool, default=True, help="if True, provide the previous output of the model as a prompt for the next window; disabling may make the text inconsistent across windows, but the model becomes less prone to getting stuck in a failure loop")
parser.add_argument("--always_use_initial_prompt", type=str2bool, default=False, help="if True, the initial_prompt will be used to all windows, and condition_on_previous_text will be ignored. Enabling this may make the text more consistent if if the audio is long and you set the initial_prompt properly.")
parser.add_argument("--fp16", type=str2bool, default=True, help="whether to perform inference in fp16; True by default")
parser.add_argument("--temperature_increment_on_fallback", type=optional_float, default=0.2, help="temperature to increase when falling back when the decoding fails to meet either of the thresholds below")