PaddleX/paddlex/inference/serving/schemas/multilingual_speech_recognition.py

# Copyright (c) 2024 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from typing import Final, List

from pydantic import BaseModel

from ..infra.models import PrimaryOperations

__all__ = [
    "INFER_ENDPOINT",
    "InferRequest",
    "Segment",
    "InferResult",
    "PRIMARY_OPERATIONS",
]

INFER_ENDPOINT: Final[str] = "/multilingual-speech-recognition"


class InferRequest(BaseModel):
    audio: str


class Segment(BaseModel):
    id: int
    seek: int
    start: float
    end: float
    text: str
    tokens: List[int]
    temperature: float
    avgLogProb: float
    compressionRatio: float
    noSpeechProb: float


class InferResult(BaseModel):
    text: str
    segments: List[Segment]
    language: str


PRIMARY_OPERATIONS: Final[PrimaryOperations] = {
    "infer": (INFER_ENDPOINT, InferRequest, InferResult),
}