microsoft/onnxruntime-extensions
Publicmirrored fromhttps://github.com/microsoft/onnxruntime-extensionsAvailable
include/ortx_extractor.h
75lines · modecode
| 1 | // Copyright (c) Microsoft Corporation. All rights reserved. |
| 2 | // Licensed under the MIT License. |
| 3 | |
| 4 | // C ABI header file for the onnxruntime-extensions tokenization module |
| 5 | |
| 6 | #pragma once |
| 7 | |
| 8 | #include "ortx_utils.h" |
| 9 | |
| 10 | typedef OrtxObject OrtxFeatureExtractor; |
| 11 | typedef OrtxObject OrtxRawAudios; |
| 12 | typedef OrtxObject OrtxTensorResult; |
| 13 | |
| 14 | #ifdef __cplusplus |
| 15 | extern "C" { |
| 16 | #endif |
| 17 | |
| 18 | /** |
| 19 | * @brief Creates a feature extractor object. |
| 20 | * |
| 21 | * This function creates a feature extractor object based on the provided feature definition. |
| 22 | * |
| 23 | * @param[out] extractor Pointer to a pointer to the created feature extractor object. |
| 24 | * @param[in] fe_def The feature definition used to create the feature extractor. |
| 25 | * |
| 26 | * @return An error code indicating the result of the operation. |
| 27 | */ |
| 28 | extError_t ORTX_API_CALL OrtxCreateSpeechFeatureExtractor(OrtxFeatureExtractor** extractor, const char* fe_def); |
| 29 | |
| 30 | /** |
| 31 | * Loads a collection of audio files into memory. |
| 32 | * |
| 33 | * This function loads a collection of audio files specified by the `audio_paths` array |
| 34 | * into memory and returns a pointer to the loaded audio data in the `audios` parameter. |
| 35 | * |
| 36 | * @param audios A pointer to a pointer that will be updated with the loaded audio data. |
| 37 | * The caller is responsible for freeing the memory allocated for the audio data. |
| 38 | * @param audio_paths An array of strings representing the paths to the audio files to be loaded. |
| 39 | * @param num_audios The number of audio files to be loaded. |
| 40 | * |
| 41 | * @return An `extError_t` value indicating the success or failure of the operation. |
| 42 | */ |
| 43 | extError_t ORTX_API_CALL OrtxLoadAudios(OrtxRawAudios** audios, const char* const* audio_paths, size_t num_audios); |
| 44 | |
| 45 | /** |
| 46 | * @brief Creates an array of raw audio objects. |
| 47 | * |
| 48 | * This function creates an array of raw audio objects based on the provided data and sizes. |
| 49 | * |
| 50 | * @param audios Pointer to the variable that will hold the created raw audio objects. |
| 51 | * @param data Array of pointers to the audio data. |
| 52 | * @param sizes Array of pointers to the sizes of the audio data. |
| 53 | * @param num_audios Number of audio objects to create. |
| 54 | * |
| 55 | * @return extError_t Error code indicating the success or failure of the operation. |
| 56 | */ |
| 57 | extError_t ORTX_API_CALL OrtxCreateRawAudios(OrtxRawAudios** audios, const void* data[], const int64_t* sizes[], size_t num_audios); |
| 58 | |
| 59 | /** |
| 60 | * @brief Calculates the log mel spectrogram for a given audio using the specified feature extractor. |
| 61 | * |
| 62 | * This function takes an instance of the OrtxFeatureExtractor struct, an instance of the OrtxRawAudios struct, |
| 63 | * and a pointer to a OrtxTensorResult pointer. It calculates the log mel spectrogram for the given audio using |
| 64 | * the specified feature extractor and stores the result in the provided log_mel pointer. |
| 65 | * |
| 66 | * @param extractor The feature extractor to use for calculating the log mel spectrogram. |
| 67 | * @param audio The raw audio data to process. |
| 68 | * @param log_mel A pointer to a OrtxTensorResult pointer where the result will be stored. |
| 69 | * @return An extError_t value indicating the success or failure of the operation. |
| 70 | */ |
| 71 | extError_t ORTX_API_CALL OrtxSpeechLogMel(OrtxFeatureExtractor* extractor, OrtxRawAudios* audio, OrtxTensorResult** log_mel); |
| 72 | |
| 73 | #ifdef __cplusplus |
| 74 | } |
| 75 | #endif |
| 76 | |