Mirroristas/whisper
2
0
Fork 0
mirror of https://github.com/openai/whisper.git synced 2025-03-30 14:28:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Context prompt (#128)

Browse Source 
Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
This commit is contained in:
VulumeCode 2022-09-26 14:22:33 +02:00 committed by GitHub
parent fc0f40981d
commit 2037b65f3f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
whisper/transcribe.py
View File

@ -137,6 +137,11 @@ def transcribe(
all_segments = []
prompt_reset_since = 0
initial_prompt = decode_options.pop("initial_prompt", None) or []
if initial_prompt:
initial_prompt = tokenizer.encode(" " + initial_prompt.strip())
all_tokens.extend(initial_prompt)
def add_segment(
*, start: float, end: float, text_tokens: torch.Tensor, result: DecodingResult
):
@ -237,7 +242,7 @@ def transcribe(
pbar.update(min(num_frames, seek) - previous_seek_value)
previous_seek_value = seek
return dict(text=tokenizer.decode(all_tokens), segments=all_segments, language=language)
return dict(text=tokenizer.decode(all_tokens[len(initial_prompt):]), segments=all_segments, language=language)
def cli():
@ -260,6 +265,7 @@ def cli():
parser.add_argument("--length_penalty", type=float, default=None, help="optional token length penalty coefficient (alpha) as in https://arxiv.org/abs/1609.08144, uses simple lengt 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")
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("--fp16", type=str2bool, default=True, help="whether to perform inference in fp16; True by default")