first commit
This commit is contained in:
150
docs/openapi/schemas/inference/transcription.yaml
Normal file
150
docs/openapi/schemas/inference/transcription.yaml
Normal file
@@ -0,0 +1,150 @@
|
||||
# Transcription API schemas
|
||||
|
||||
TranscriptionRequest:
|
||||
type: object
|
||||
required:
|
||||
- model
|
||||
- file
|
||||
properties:
|
||||
model:
|
||||
type: string
|
||||
description: Model in provider/model format
|
||||
file:
|
||||
type: string
|
||||
format: binary
|
||||
description: Audio file to transcribe
|
||||
fallbacks:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
stream:
|
||||
type: boolean
|
||||
language:
|
||||
type: string
|
||||
prompt:
|
||||
type: string
|
||||
response_format:
|
||||
type: string
|
||||
enum: [json, text, srt, verbose_json, vtt]
|
||||
file_format:
|
||||
type: string
|
||||
|
||||
TranscriptionResponse:
|
||||
type: object
|
||||
properties:
|
||||
duration:
|
||||
type: number
|
||||
language:
|
||||
type: string
|
||||
logprobs:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/TranscriptionLogProb'
|
||||
segments:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/TranscriptionSegment'
|
||||
task:
|
||||
type: string
|
||||
text:
|
||||
type: string
|
||||
usage:
|
||||
$ref: '#/TranscriptionUsage'
|
||||
words:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/TranscriptionWord'
|
||||
extra_fields:
|
||||
$ref: './common.yaml#/BifrostResponseExtraFields'
|
||||
|
||||
TranscriptionLogProb:
|
||||
type: object
|
||||
properties:
|
||||
token:
|
||||
type: string
|
||||
logprob:
|
||||
type: number
|
||||
bytes:
|
||||
type: array
|
||||
items:
|
||||
type: integer
|
||||
|
||||
TranscriptionSegment:
|
||||
type: object
|
||||
properties:
|
||||
id:
|
||||
type: integer
|
||||
seek:
|
||||
type: integer
|
||||
start:
|
||||
type: number
|
||||
end:
|
||||
type: number
|
||||
text:
|
||||
type: string
|
||||
tokens:
|
||||
type: array
|
||||
items:
|
||||
type: integer
|
||||
temperature:
|
||||
type: number
|
||||
avg_logprob:
|
||||
type: number
|
||||
compression_ratio:
|
||||
type: number
|
||||
no_speech_prob:
|
||||
type: number
|
||||
|
||||
TranscriptionWord:
|
||||
type: object
|
||||
properties:
|
||||
word:
|
||||
type: string
|
||||
start:
|
||||
type: number
|
||||
end:
|
||||
type: number
|
||||
|
||||
TranscriptionUsage:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
enum: [tokens, duration]
|
||||
input_tokens:
|
||||
type: integer
|
||||
input_token_details:
|
||||
$ref: '#/TranscriptionUsageInputTokenDetails'
|
||||
output_tokens:
|
||||
type: integer
|
||||
total_tokens:
|
||||
type: integer
|
||||
seconds:
|
||||
type: integer
|
||||
|
||||
TranscriptionUsageInputTokenDetails:
|
||||
type: object
|
||||
properties:
|
||||
text_tokens:
|
||||
type: integer
|
||||
audio_tokens:
|
||||
type: integer
|
||||
|
||||
TranscriptionStreamResponse:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
enum: [transcript.text.delta, transcript.text.done]
|
||||
delta:
|
||||
type: string
|
||||
logprobs:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/TranscriptionLogProb'
|
||||
text:
|
||||
type: string
|
||||
usage:
|
||||
$ref: '#/TranscriptionUsage'
|
||||
extra_fields:
|
||||
$ref: './common.yaml#/BifrostResponseExtraFields'
|
||||
Reference in New Issue
Block a user