Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Commite043d7b

Browse files
apcha-oaistainless-app[bot]
authored andcommitted
chore: fix dangling comment
1 parent25cbb74 commite043d7b

File tree

1 file changed

+0
-60
lines changed

1 file changed

+0
-60
lines changed

‎src/openai/resources/audio/transcriptions.py‎

Lines changed: 0 additions & 60 deletions
Original file line numberDiff line numberDiff line change
@@ -103,66 +103,6 @@ def create(
103103
timeout:float|httpx.Timeout|None|NotGiven=not_given,
104104
)->TranscriptionVerbose: ...
105105

106-
model'sconfidenceinthetranscription.`logprobs`onlyworkswith
107-
response_formatsetto`json`andonlywiththemodels`gpt-4o-transcribe`and
108-
`gpt-4o-mini-transcribe`.Thisfieldisnotsupportedwhenusing
109-
`gpt-4o-transcribe-diarize`.
110-
111-
known_speaker_names:Optionallistofspeakernamesthatcorrespondtotheaudiosamplesprovidedin
112-
`known_speaker_references[]`.Eachentryshouldbeashortidentifier (for
113-
example`customer`or`agent`).Upto4speakersaresupported.
114-
115-
known_speaker_references:Optionallistofaudiosamples (as
116-
[dataURLs](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs))
117-
thatcontainknownspeakerreferencesmatching`known_speaker_names[]`.Each
118-
samplemustbebetween2and10seconds,andcanuseanyofthesameinputaudio
119-
formatssupportedby`file`.
120-
121-
language:Thelanguageoftheinputaudio.Supplyingtheinputlanguagein
122-
[ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g.`en`)
123-
formatwillimproveaccuracyandlatency.
124-
125-
prompt:Anoptionaltexttoguidethemodel'sstyleorcontinueapreviousaudio
126-
segment.The
127-
[prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
128-
shouldmatchtheaudiolanguage.Thisfieldisnotsupportedwhenusing
129-
`gpt-4o-transcribe-diarize`.
130-
131-
response_format:Theformatoftheoutput,inoneoftheseoptions:`json`,`text`,`srt`,
132-
`verbose_json`,`vtt`,or`diarized_json`.For`gpt-4o-transcribe`and
133-
`gpt-4o-mini-transcribe`,theonlysupportedformatis`json`.For
134-
`gpt-4o-transcribe-diarize`,thesupportedformatsare`json`,`text`,and
135-
`diarized_json`,with`diarized_json`requiredtoreceivespeakerannotations.
136-
137-
stream:Ifsettotrue,themodelresponsedatawillbestreamedtotheclientasitis
138-
generatedusing
139-
[server-sentevents](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
140-
Seethe
141-
[StreamingsectionoftheSpeech-to-Textguide](https://platform.openai.com/docs/guides/speech-to-text?lang=curl#streaming-transcriptions)
142-
formoreinformation.
143-
144-
Note:Streamingisnotsupportedforthe`whisper-1`modelandwillbeignored.
145-
146-
temperature:Thesamplingtemperature,between0and1.Highervalueslike0.8willmakethe
147-
outputmorerandom,whilelowervalueslike0.2willmakeitmorefocusedand
148-
deterministic.Ifsetto0,themodelwilluse
149-
[logprobability](https://en.wikipedia.org/wiki/Log_probability)to
150-
automaticallyincreasethetemperatureuntilcertainthresholdsarehit.
151-
152-
timestamp_granularities:Thetimestampgranularitiestopopulateforthistranscription.
153-
`response_format`mustbeset`verbose_json`tousetimestampgranularities.
154-
Eitherorbothoftheseoptionsaresupported:`word`,or`segment`.Note:There
155-
isnoadditionallatencyforsegmenttimestamps,butgeneratingwordtimestamps
156-
incursadditionallatency.Thisoptionisnotavailablefor
157-
`gpt-4o-transcribe-diarize`.
158-
159-
extra_headers:Sendextraheaders
160-
161-
extra_query:Addadditionalqueryparameterstotherequest
162-
163-
extra_body:AddadditionalJSONpropertiestotherequest
164-
)->Transcription: ...
165-
166106
@overload
167107
defcreate(
168108
self,

0 commit comments

Comments
 (0)

[8]ページ先頭

©2009-2025 Movatter.jp