[Frontend] Add /v1/audio/transcriptions OpenAI API endpoint (#12909)

vllm/entrypoints/openai/protocol.py

@@ -8,9 +8,10 @@ from argparse import Namespace
 from typing import Any, ClassVar, Dict, List, Literal, Optional, Set, Union
 
 import torch
+from fastapi import UploadFile
 from pydantic import (BaseModel, ConfigDict, Field, TypeAdapter,
                       ValidationInfo, field_validator, model_validator)
-from typing_extensions import Annotated
+from typing_extensions import Annotated, TypeAlias
 
 from vllm.entrypoints.chat_utils import ChatCompletionMessageParam
 from vllm.logger import init_logger
@@ -1426,3 +1427,163 @@ class LoadLoraAdapterRequest(BaseModel):
 class UnloadLoraAdapterRequest(BaseModel):
     lora_name: str
     lora_int_id: Optional[int] = Field(default=None)
+
+
+## Protocols for Audio
+AudioResponseFormat: TypeAlias = Literal["json", "text", "srt", "verbose_json",
+                                         "vtt"]
+
+
+class TranscriptionRequest(OpenAIBaseModel):
+    # Ordered by official OpenAI API documentation
+    #https://platform.openai.com/docs/api-reference/audio/createTranscription
+
+    file: UploadFile
+    """
+    The audio file object (not file name) to transcribe, in one of these
+    formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
+    """
+
+    model: str
+    """ID of the model to use.
+    """
+
+    language: Optional[str] = None
+    """The language of the input audio.
+
+    Supplying the input language in
+    [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format
+    will improve accuracy and latency.
+    """
+
+    prompt: str = Field(default="")
+    """An optional text to guide the model's style or continue a previous audio
+    segment.
+
+    The [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting)
+    should match the audio language.
+    """
+
+    response_format: AudioResponseFormat = Field(default="json")
+    """
+    The format of the output, in one of these options: `json`, `text`, `srt`,
+    `verbose_json`, or `vtt`.
+    """
+
+    ## TODO (varun) : Support if set to 0, certain thresholds are met !!
+    temperature: float = Field(default=0.0)
+    """The sampling temperature, between 0 and 1.
+
+    Higher values like 0.8 will make the output more random, while lower values
+    like 0.2 will make it more focused / deterministic. If set to 0, the model
+    will use [log probability](https://en.wikipedia.org/wiki/Log_probability)
+    to automatically increase the temperature until certain thresholds are hit.
+    """
+
+    timestamp_granularities: List[Literal["word", "segment"]] = Field(
+        alias="timestamp_granularities[]", default=[])
+    """The timestamp granularities to populate for this transcription.
+
+    `response_format` must be set `verbose_json` to use timestamp granularities.
+    Either or both of these options are supported: `word`, or `segment`. Note:
+    There is no additional latency for segment timestamps, but generating word
+    timestamps incurs additional latency.
+    """
+
+    # Default sampling parameters for transcription requests.
+    _DEFAULT_SAMPLING_PARAMS: dict = {
+        "temperature": 0,
+    }
+
+    def to_sampling_params(
+            self,
+            default_max_tokens: int,
+            default_sampling_params: Optional[dict] = None) -> SamplingParams:
+        # TODO(#9845): remove max_tokens when field is removed from OpenAI API
+        max_tokens = default_max_tokens
+
+        if default_sampling_params is None:
+            default_sampling_params = {}
+        # Default parameters
+        if (temperature := self.temperature) is None:
+            temperature = default_sampling_params.get(
+                "temperature", self._DEFAULT_SAMPLING_PARAMS["temperature"])
+
+        return SamplingParams.from_optional(temperature=temperature,
+                                            max_tokens=max_tokens)
+
+
+# Transcription response objects
+class TranscriptionResponse(OpenAIBaseModel):
+    text: str
+    """The transcribed text."""
+
+
+class TranscriptionWord(OpenAIBaseModel):
+    end: float
+    """End time of the word in seconds."""
+
+    start: float
+    """Start time of the word in seconds."""
+
+    word: str
+    """The text content of the word."""
+
+
+class TranscriptionSegment(OpenAIBaseModel):
+    id: int
+    """Unique identifier of the segment."""
+
+    avg_logprob: float
+    """Average logprob of the segment.
+
+    If the value is lower than -1, consider the logprobs failed.
+    """
+
+    compression_ratio: float
+    """Compression ratio of the segment.
+
+    If the value is greater than 2.4, consider the compression failed.
+    """
+
+    end: float
+    """End time of the segment in seconds."""
+
+    no_speech_prob: float
+    """Probability of no speech in the segment.
+
+    If the value is higher than 1.0 and the `avg_logprob` is below -1, consider
+    this segment silent.
+    """
+
+    seek: int
+    """Seek offset of the segment."""
+
+    start: float
+    """Start time of the segment in seconds."""
+
+    temperature: float
+    """Temperature parameter used for generating the segment."""
+
+    text: str
+    """Text content of the segment."""
+
+    tokens: List[int]
+    """Array of token IDs for the text content."""
+
+
+class TranscriptionResponseVerbose(OpenAIBaseModel):
+    duration: str
+    """The duration of the input audio."""
+
+    language: str
+    """The language of the input audio."""
+
+    text: str
+    """The transcribed text."""
+
+    segments: Optional[List[TranscriptionSegment]] = None
+    """Segments of the transcribed text and their corresponding details."""
+
+    words: Optional[List[TranscriptionWord]] = None
+    """Extracted words and their corresponding timestamps."""