Skip to content

fix: use default whisper temperature values for temperature 0.0 like openai api #615

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
dotmobo wants to merge 1 commit into
base: master
Choose a base branch
from
Open

fix: use default whisper temperature values for temperature 0.0 like openai api #615

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/speaches/executors/shared/handler_protocol.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,7 @@ class TranscriptionRequest(BaseModel):
language: str | None = None
prompt: str | None = None
response_format: openai.types.AudioResponseFormat = "json"
temperature: float = 0.0
temperature: float | list[float] = 0.0
hotwords: str | None = None
timestamp_granularities: TimestampGranularities
speech_segments: list[SpeechTimestamp]
Expand Down Expand Up @@ -103,7 +103,7 @@ class TranslationRequest(BaseModel):
model: str
prompt: str | None = None
response_format: openai.types.AudioResponseFormat = "json"
temperature: float = 0.0
temperature: float | list[float] = 0.0
speech_segments: list[SpeechTimestamp]
vad_options: VadOptions

Expand Down
8 changes: 4 additions & 4 deletions src/speaches/routers/stt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@ def translate_file(
model: Annotated[ModelId, Form()],
prompt: Annotated[str | None, Form()] = None,
response_format: Annotated[ResponseFormat, Form()] = DEFAULT_RESPONSE_FORMAT,
temperature: Annotated[float, Form()] = 0.0,
temperature: Annotated[float | list[float], Form()] = 0.0,
) -> Response:
model_card_data = get_model_card_data_or_raise(model)
executor = find_executor_for_model_or_raise(model, model_card_data, executor_registry.translation)
Expand All @@ -79,7 +79,7 @@ def translate_file(
model=model,
prompt=prompt,
response_format=response_format,
temperature=temperature,
temperature=temperature if temperature != 0.0 else [0.0, 0.2, 0.4, 0.6, 0.8, 1.0],
speech_segments=speech_segments,
vad_options=DEFAULT_VAD_OPTIONS,
)
Expand Down Expand Up @@ -129,7 +129,7 @@ def transcribe_file(
language: Annotated[str | None, Form()] = None,
prompt: Annotated[str | None, Form()] = None,
response_format: Annotated[ResponseFormat, Form()] = DEFAULT_RESPONSE_FORMAT,
temperature: Annotated[float, Form()] = 0.0,
temperature: Annotated[float | list[float], Form()] = 0.0,
timestamp_granularities: Annotated[
TimestampGranularities,
# WARN: `alias` doesn't actually work.
Expand Down Expand Up @@ -160,7 +160,7 @@ def transcribe_file(
language=language,
prompt=prompt,
response_format=response_format,
temperature=temperature,
temperature=temperature if temperature != 0.0 else [0.0, 0.2, 0.4, 0.6, 0.8, 1.0],
timestamp_granularities=timestamp_granularities,
stream=stream,
hotwords=hotwords,
Expand Down