[Frontend] add 'verbose_json' and 'timestamp' feature on Whisper Transcription/Translation (#24209)
Signed-off-by: sangbumlikeagod <oironese@naver.com> Signed-off-by: sangbumlikeagod <98077576+sangbumlikeagod@users.noreply.github.com>
This commit is contained in:
@@ -2126,13 +2126,13 @@ class TranscriptionSegment(OpenAIBaseModel):
|
||||
id: int
|
||||
"""Unique identifier of the segment."""
|
||||
|
||||
avg_logprob: float
|
||||
avg_logprob: float | None = None
|
||||
"""Average logprob of the segment.
|
||||
|
||||
If the value is lower than -1, consider the logprobs failed.
|
||||
"""
|
||||
|
||||
compression_ratio: float
|
||||
compression_ratio: float | None = None
|
||||
"""Compression ratio of the segment.
|
||||
|
||||
If the value is greater than 2.4, consider the compression failed.
|
||||
@@ -2141,7 +2141,7 @@ class TranscriptionSegment(OpenAIBaseModel):
|
||||
end: float
|
||||
"""End time of the segment in seconds."""
|
||||
|
||||
no_speech_prob: float
|
||||
no_speech_prob: float | None = None
|
||||
"""Probability of no speech in the segment.
|
||||
|
||||
If the value is higher than 1.0 and the `avg_logprob` is below -1, consider
|
||||
@@ -2181,6 +2181,11 @@ class TranscriptionResponseVerbose(OpenAIBaseModel):
|
||||
"""Extracted words and their corresponding timestamps."""
|
||||
|
||||
|
||||
TranscriptionResponseVariant: TypeAlias = (
|
||||
TranscriptionResponse | TranscriptionResponseVerbose
|
||||
)
|
||||
|
||||
|
||||
class TranslationResponseStreamChoice(OpenAIBaseModel):
|
||||
delta: DeltaMessage
|
||||
finish_reason: str | None = None
|
||||
@@ -2325,13 +2330,13 @@ class TranslationSegment(OpenAIBaseModel):
|
||||
id: int
|
||||
"""Unique identifier of the segment."""
|
||||
|
||||
avg_logprob: float
|
||||
avg_logprob: float | None = None
|
||||
"""Average logprob of the segment.
|
||||
|
||||
If the value is lower than -1, consider the logprobs failed.
|
||||
"""
|
||||
|
||||
compression_ratio: float
|
||||
compression_ratio: float | None = None
|
||||
"""Compression ratio of the segment.
|
||||
|
||||
If the value is greater than 2.4, consider the compression failed.
|
||||
@@ -2340,7 +2345,7 @@ class TranslationSegment(OpenAIBaseModel):
|
||||
end: float
|
||||
"""End time of the segment in seconds."""
|
||||
|
||||
no_speech_prob: float
|
||||
no_speech_prob: float | None = None
|
||||
"""Probability of no speech in the segment.
|
||||
|
||||
If the value is higher than 1.0 and the `avg_logprob` is below -1, consider
|
||||
@@ -2380,6 +2385,9 @@ class TranslationResponseVerbose(OpenAIBaseModel):
|
||||
"""Extracted words and their corresponding timestamps."""
|
||||
|
||||
|
||||
TranslationResponseVariant: TypeAlias = TranslationResponse | TranslationResponseVerbose
|
||||
|
||||
|
||||
####### Tokens IN <> Tokens OUT #######
|
||||
class GenerateRequest(BaseModel):
|
||||
request_id: str = Field(
|
||||
|
||||
Reference in New Issue
Block a user