module aixplain.modules.pipeline.pipeline
class ObjectDetectionInputs
method __init__
__init__(node=None)
class ObjectDetectionOutputs
method __init__
__init__(node=None)
class ObjectDetection
Object Detection is a computer vision technology that identifies and locates objects within an image, typically by drawing bounding boxes around the detected objects and classifying them into predefined categories.
InputType: video OutputType: text
class LanguageIdentificationInputs
method __init__
__init__(node=None)
class LanguageIdentificationOutputs
method __init__
__init__(node=None)
class LanguageIdentification
Language Identification is the process of automatically determining the language in which a given piece of text is written.
InputType: text OutputType: text
class OcrInputs
method __init__
__init__(node=None)
class OcrOutputs
method __init__
__init__(node=None)
class Ocr
OCR, or Optical Character Recognition, is a technology that converts different types of documents, such as scanned paper documents, PDFs, or images captured by a digital camera, into editable and searchable data by recognizing and extracting text from the images.
InputType: image OutputType: text
class ScriptExecutionInputs
method __init__
__init__(node=None)
class ScriptExecutionOutputs
method __init__
__init__(node=None)
class ScriptExecution
Script Execution refers to the process of running a set of programmed instructions or code within a computing environment, enabling the automated performance of tasks, calculations, or operations as defined by the script.
InputType: text OutputType: text
class ImageLabelDetectionInputs
method __init__
__init__(node=None)
class ImageLabelDetectionOutputs
method __init__
__init__(node=None)
class ImageLabelDetection
Image Label Detection is a function that automatically identifies and assigns descriptive tags or labels to objects, scenes, or elements within an image, enabling easier categorization, search, and analysis of visual content.
InputType: image OutputType: label
class ImageCaptioningInputs
method __init__
__init__(node=None)
class ImageCaptioningOutputs
method __init__
__init__(node=None)
class ImageCaptioning
Image Captioning is a process that involves generating a textual description of an image, typically using machine learning models to analyze the visual content and produce coherent and contextually relevant sentences that describe the objects, actions, and scenes depicted in the image.
InputType: image OutputType: text
class AudioLanguageIdentificationInputs
method __init__
__init__(node=None)
class AudioLanguageIdentificationOutputs
method __init__
__init__(node=None)
class AudioLanguageIdentification
Audio Language Identification is a process that involves analyzing an audio recording to determine the language being spoken.
InputType: audio OutputType: label
class AsrAgeClassificationInputs
method __init__
__init__(node=None)
class AsrAgeClassificationOutputs
method __init__
__init__(node=None)
class AsrAgeClassification
The ASR Age Classification function is designed to analyze audio recordings of speech to determine the speaker's age group by leveraging automatic speech recognition (ASR) technology and machine learning algorithms.
InputType: audio OutputType: label
class BenchmarkScoringMtInputs
method __init__
__init__(node=None)
class BenchmarkScoringMtOutputs
method __init__
__init__(node=None)
class BenchmarkScoringMt
Benchmark Scoring MT is a function designed to evaluate and score machine translation systems by comparing their output against a set of predefined benchmarks, thereby assessing their accuracy and performance.
InputType: text OutputType: label
class AsrGenderClassificationInputs
method __init__
__init__(node=None)
class AsrGenderClassificationOutputs
method __init__
__init__(node=None)
class AsrGenderClassification
The ASR Gender Classification function analyzes audio recordings to determine and classify the speaker's gender based on their voice characteristics.
InputType: audio OutputType: label
class BaseModelInputs
method __init__
__init__(node=None)
class BaseModelOutputs
method __init__
__init__(node=None)
class BaseModel
The Base-Model function serves as a foundational framework designed to provide essential features and capabilities upon which more specialized or advanced models can be built and customized.
InputType: text OutputType: text
class LanguageIdentificationAudioInputs
method __init__
__init__(node=None)
class LanguageIdentificationAudioOutputs
method __init__
__init__(node=None)
class LanguageIdentificationAudio
The Language Identification Audio function analyzes audio input to determine and identify the language being spoken.
InputType: audio OutputType: label
class LoglikelihoodInputs
method __init__
__init__(node=None)
class LoglikelihoodOutputs
method __init__
__init__(node=None)
class Loglikelihood
The Log Likelihood function measures the probability of observing the given data under a specific statistical model by taking the natural logarithm of the likelihood function, thereby transforming the product of probabilities into a sum, which simplifies the process of optimization and parameter estimation.
InputType: text OutputType: number
class VideoEmbeddingInputs
method __init__
__init__(node=None)
class VideoEmbeddingOutputs
method __init__
__init__(node=None)
class VideoEmbedding
Video Embedding is a process that transforms video content into a fixed- dimensional vector representation, capturing essential features and patterns to facilitate tasks such as retrieval, classification, and recommendation.
InputType: video OutputType: embedding
class TextSegmenationInputs
method __init__
__init__(node=None)
class TextSegmenationOutputs
method __init__
__init__(node=None)
class TextSegmenation
Text Segmentation is the process of dividing a continuous text into meaningful units, such as words, sentences, or topics, to facilitate easier analysis and understanding.
InputType: text OutputType: text
class ImageEmbeddingInputs
method __init__
__init__(node=None)
class ImageEmbeddingOutputs
method __init__
__init__(node=None)
class ImageEmbedding
Image Embedding is a process that transforms an image into a fixed-dimensional vector representation, capturing its essential features and enabling efficient comparison, retrieval, and analysis in various machine learning and computer vision tasks.
InputType: image OutputType: text
class ImageManipulationInputs
method __init__
__init__(node=None)
class ImageManipulationOutputs
method __init__
__init__(node=None)
class ImageManipulation
Image Manipulation refers to the process of altering or enhancing digital images using various techniques and tools to achieve desired visual effects, correct imperfections, or transform the image's appearance.
InputType: image OutputType: image
class ImageToVideoGenerationInputs
method __init__
__init__(node=None)
class ImageToVideoGenerationOutputs
method __init__
__init__(node=None)
class ImageToVideoGeneration
The Image To Video Generation function transforms a series of static images into a cohesive, dynamic video sequence, often incorporating transitions, effects, and synchronization with audio to create a visually engaging narrative.
InputType: image OutputType: video
class AudioForcedAlignmentInputs
method __init__
__init__(node=None)
class AudioForcedAlignmentOutputs
method __init__
__init__(node=None)
class AudioForcedAlignment
Audio Forced Alignment is a process that synchronizes a given audio recording with its corresponding transcript by precisely aligning each spoken word or phoneme to its exact timing within the audio.
InputType: audio OutputType: audio
class BenchmarkScoringAsrInputs
method __init__
__init__(node=None)
class BenchmarkScoringAsrOutputs
method __init__
__init__(node=None)
class BenchmarkScoringAsr
Benchmark Scoring ASR is a function that evaluates and compares the performance of automatic speech recognition systems by analyzing their accuracy, speed, and other relevant metrics against a standardized set of benchmarks.
InputType: audio OutputType: label
class VisualQuestionAnsweringInputs
method __init__
__init__(node=None)
class VisualQuestionAnsweringOutputs
method __init__
__init__(node=None)
class VisualQuestionAnswering
Visual Question Answering (VQA) is a task in artificial intelligence that involves analyzing an image and providing accurate, contextually relevant answers to questions posed about the visual content of that image.
InputType: image OutputType: video
class DocumentImageParsingInputs
method __init__
__init__(node=None)
class DocumentImageParsingOutputs
method __init__
__init__(node=None)
class DocumentImageParsing
Document Image Parsing is the process of analyzing and converting scanned or photographed images of documents into structured, machine-readable formats by identifying and extracting text, layout, and other relevant information.
InputType: image OutputType: text
class DocumentInformationExtractionInputs
method __init__
__init__(node=None)
class DocumentInformationExtractionOutputs
method __init__
__init__(node=None)
class DocumentInformationExtraction
Document Information Extraction is the process of automatically identifying, extracting, and structuring relevant data from unstructured or semi-structured documents, such as invoices, receipts, contracts, and forms, to facilitate easier data management and analysis.
InputType: image OutputType: text
class DepthEstimationInputs
method __init__
__init__(node=None)
class DepthEstimationOutputs
method __init__
__init__(node=None)
class DepthEstimation
Depth estimation is a computational process that determines the distance of objects from a viewpoint, typically using visual data from cameras or sensors to create a three-dimensional understanding of a scene.
InputType: image OutputType: text
class VideoGenerationInputs
method __init__
__init__(node=None)
class VideoGenerationOutputs
method __init__
__init__(node=None)
class VideoGeneration
Video Generation is the process of creating video content through automated or semi-automated means, often utilizing algorithms, artificial intelligence, or software tools to produce visual and audio elements that can range from simple animations to complex, realistic scenes.
InputType: text OutputType: video
class ReferencelessAudioGenerationMetricInputs
method __init__
__init__(node=None)
class ReferencelessAudioGenerationMetricOutputs
method __init__
__init__(node=None)
class ReferencelessAudioGenerationMetric
The Referenceless Audio Generation Metric is a tool designed to evaluate the quality of generated audio content without the need for a reference or original audio sample for comparison.
InputType: text OutputType: text
class MultiClassImageClassificationInputs
method __init__
__init__(node=None)
class MultiClassImageClassificationOutputs
method __init__
__init__(node=None)
class MultiClassImageClassification
Multi Class Image Classification is a machine learning task where an algorithm is trained to categorize images into one of several predefined classes or categories based on their visual content.
InputType: image OutputType: label
class SemanticSegmentationInputs
method __init__
__init__(node=None)
class SemanticSegmentationOutputs
method __init__
__init__(node=None)
class SemanticSegmentation
Semantic segmentation is a computer vision process that involves classifying each pixel in an image into a predefined category, effectively partitioning the image into meaningful segments based on the objects or regions they represent.
InputType: image OutputType: label
class InstanceSegmentationInputs
method __init__
__init__(node=None)
class InstanceSegmentationOutputs
method __init__
__init__(node=None)
class InstanceSegmentation
Instance segmentation is a computer vision task that involves detecting and delineating each distinct object within an image, assigning a unique label and precise boundary to every individual instance of objects, even if they belong to the same category.
InputType: image OutputType: label
class ImageColorizationInputs
method __init__
__init__(node=None)
class ImageColorizationOutputs
method __init__
__init__(node=None)
class ImageColorization
Image colorization is a process that involves adding color to grayscale images, transforming them from black-and-white to full-color representations, often using advanced algorithms and machine learning techniques to predict and apply the appropriate hues and shades.
InputType: image OutputType: image
class AudioGenerationMetricInputs
method __init__
__init__(node=None)
class AudioGenerationMetricOutputs
method __init__
__init__(node=None)
class AudioGenerationMetric
The Audio Generation Metric is a quantitative measure used to evaluate the quality, accuracy, and overall performance of audio generated by artificial intelligence systems, often considering factors such as fidelity, intelligibility, and similarity to human-produced audio.
InputType: text OutputType: text
class ImageImpaintingInputs
method __init__
__init__(node=None)
class ImageImpaintingOutputs
method __init__
__init__(node=None)
class ImageImpainting
Image inpainting is a process that involves filling in missing or damaged parts of an image in a way that is visually coherent and seamlessly blends with the surrounding areas, often using advanced algorithms and techniques to restore the image to its original or intended appearance.
InputType: image OutputType: image
class StyleTransferInputs
method __init__
__init__(node=None)
class StyleTransferOutputs
method __init__
__init__(node=None)
class StyleTransfer
Style Transfer is a technique in artificial intelligence that applies the visual style of one image (such as the brushstrokes of a famous painting) to the content of another image, effectively blending the artistic elements of the first image with the subject matter of the second.
InputType: image OutputType: image
class MultiClassTextClassificationInputs
method __init__
__init__(node=None)
class MultiClassTextClassificationOutputs
method __init__
__init__(node=None)
class MultiClassTextClassification
Multi Class Text Classification is a natural language processing task that involves categorizing a given text into one of several predefined classes or categories based on its content.
InputType: text OutputType: label
class TextEmbeddingInputs
method __init__
__init__(node=None)
class TextEmbeddingOutputs
method __init__
__init__(node=None)
class TextEmbedding
Text embedding is a process that converts text into numerical vectors, capturing the semantic meaning and contextual relationships of words or phrases, enabling machines to understand and analyze natural language more effectively.
InputType: text OutputType: text
class MultiLabelTextClassificationInputs
method __init__
__init__(node=None)
class MultiLabelTextClassificationOutputs
method __init__
__init__(node=None)
class MultiLabelTextClassification
Multi Label Text Classification is a natural language processing task where a given text is analyzed and assigned multiple relevant labels or categories from a predefined set, allowing for the text to belong to more than one category simultaneously.
InputType: text OutputType: label
class TextReconstructionInputs
method __init__
__init__(node=None)
class TextReconstructionOutputs
method __init__
__init__(node=None)
class TextReconstruction
Text Reconstruction is a process that involves piecing together fragmented or incomplete text data to restore it to its original, coherent form.
InputType: text OutputType: text
class FactCheckingInputs
method __init__
__init__(node=None)
class FactCheckingOutputs
method __init__
__init__(node=None)
class FactChecking
Fact Checking is the process of verifying the accuracy and truthfulness of information, statements, or claims by cross-referencing with reliable sources and evidence.
InputType: text OutputType: label
class SpeechClassificationInputs
method __init__
__init__(node=None)
class SpeechClassificationOutputs
method __init__
__init__(node=None)
class SpeechClassification
Speech Classification is a process that involves analyzing and categorizing spoken language into predefined categories or classes based on various features such as tone, pitch, and linguistic content.
InputType: audio OutputType: label
class IntentClassificationInputs
method __init__
__init__(node=None)
class IntentClassificationOutputs
method __init__
__init__(node=None)
class IntentClassification
Intent Classification is a natural language processing task that involves analyzing and categorizing user text input to determine the underlying purpose or goal behind the communication, such as booking a flight, asking for weather information, or setting a reminder.
InputType: text OutputType: label
class PartOfSpeechTaggingInputs
method __init__
__init__(node=None)
class PartOfSpeechTaggingOutputs
method __init__
__init__(node=None)
class PartOfSpeechTagging
Part of Speech Tagging is a natural language processing task that involves assigning each word in a sentence its corresponding part of speech, such as noun, verb, adjective, or adverb, based on its role and context within the sentence.
InputType: text OutputType: label
class MetricAggregationInputs
method __init__
__init__(node=None)
class MetricAggregationOutputs
method __init__
__init__(node=None)
class MetricAggregation
Metric Aggregation is a function that computes and summarizes numerical data by applying statistical operations, such as averaging, summing, or finding the minimum and maximum values, to provide insights and facilitate analysis of large datasets.
InputType: text OutputType: text
class DialectDetectionInputs
method __init__
__init__(node=None)
class DialectDetectionOutputs
method __init__
__init__(node=None)
class DialectDetection
Dialect Detection is a function that identifies and classifies the specific regional or social variations of a language spoken or written by an individual, enabling the recognition of distinct linguistic patterns and nuances associated with different dialects.
InputType: audio OutputType: text
class InverseTextNormalizationInputs
method __init__
__init__(node=None)
class InverseTextNormalizationOutputs
method __init__
__init__(node=None)
class InverseTextNormalization
Inverse Text Normalization is the process of converting spoken or written language in its normalized form, such as numbers, dates, and abbreviations, back into their original, more complex or detailed textual representations.
InputType: text OutputType: label
class TextToAudioInputs
method __init__
__init__(node=None)
class TextToAudioOutputs
method __init__
__init__(node=None)
class TextToAudio
The Text to Audio function converts written text into spoken words, allowing users to listen to the content instead of reading it.
InputType: text OutputType: audio
class FillTextMaskInputs
method __init__
__init__(node=None)
class FillTextMaskOutputs
method __init__
__init__(node=None)
class FillTextMask
The "Fill Text Mask" function takes a text input with masked or placeholder characters and replaces those placeholders with specified or contextually appropriate characters to generate a complete and coherent text output.
InputType: text OutputType: text
class VideoContentModerationInputs
method __init__
__init__(node=None)
class VideoContentModerationOutputs
method __init__
__init__(node=None)
class VideoContentModeration
Video Content Moderation is the process of reviewing, analyzing, and filtering video content to ensure it adheres to community guidelines, legal standards, and platform policies, thereby preventing the dissemination of inappropriate, harmful, or illegal material.
InputType: video OutputType: label
class ExtractAudioFromVideoInputs
method __init__
__init__(node=None)
class ExtractAudioFromVideoOutputs
method __init__
__init__(node=None)
class ExtractAudioFromVideo
The "Extract Audio From Video" function allows users to separate and save the audio track from a video file, enabling them to obtain just the sound without the accompanying visual content.
InputType: video OutputType: audio
class ImageCompressionInputs
method __init__
__init__(node=None)
class ImageCompressionOutputs
method __init__
__init__(node=None)
class ImageCompression
Image compression is a process that reduces the file size of an image by removing redundant or non-essential data, while maintaining an acceptable level of visual quality.
InputType: image OutputType: image
class MultilingualSpeechRecognitionInputs
method __init__
__init__(node=None)
class MultilingualSpeechRecognitionOutputs
method __init__
__init__(node=None)
class MultilingualSpeechRecognition
Multilingual Speech Recognition is a technology that enables the automatic transcription of spoken language into text across multiple languages, allowing for seamless communication and understanding in diverse linguistic contexts.
InputType: audio OutputType: text
class ReferencelessTextGenerationMetricInputs
method __init__
__init__(node=None)
class ReferencelessTextGenerationMetricOutputs
method __init__
__init__(node=None)
class ReferencelessTextGenerationMetric
The Referenceless Text Generation Metric is a method for evaluating the quality of generated text without requiring a reference text for comparison, often leveraging models or algorithms to assess coherence, relevance, and fluency based on intrinsic properties of the text itself.
InputType: text OutputType: text
class TextGenerationMetricDefaultInputs
method __init__
__init__(node=None)
class TextGenerationMetricDefaultOutputs
method __init__
__init__(node=None)
class TextGenerationMetricDefault
The "Text Generation Metric Default" function provides a standard set of evaluation metrics for assessing the quality and performance of text generation models.
InputType: text OutputType: text
class NoiseRemovalInputs
method __init__
__init__(node=None)
class NoiseRemovalOutputs
method __init__
__init__(node=None)
class NoiseRemoval
Noise Removal is a process that involves identifying and eliminating unwanted random variations or disturbances from an audio signal to enhance the clarity and quality of the underlying information.
InputType: audio OutputType: audio
class AudioReconstructionInputs
method __init__
__init__(node=None)
class AudioReconstructionOutputs
method __init__
__init__(node=None)
class AudioReconstruction
Audio Reconstruction is the process of restoring or recreating audio signals from incomplete, damaged, or degraded recordings to achieve a high-quality, accurate representation of the original sound.
InputType: audio OutputType: audio
class VoiceCloningInputs
method __init__
__init__(node=None)
class VoiceCloningOutputs
method __init__
__init__(node=None)
class VoiceCloning
Voice cloning is a technology that uses artificial intelligence to create a digital replica of a person's voice, allowing for the generation of speech that mimics the tone, pitch, and speaking style of the original speaker.
InputType: text OutputType: audio
class DiacritizationInputs
method __init__
__init__(node=None)
class DiacritizationOutputs
method __init__
__init__(node=None)
class Diacritization
Diacritization is the process of adding diacritical marks to letters in a text to indicate pronunciation, stress, tone, or meaning, often used in languages such as Arabic, Hebrew, and Vietnamese to provide clarity and accuracy in written communication.
InputType: text OutputType: text
class AudioEmotionDetectionInputs
method __init__
__init__(node=None)
class AudioEmotionDetectionOutputs
method __init__
__init__(node=None)
class AudioEmotionDetection
Audio Emotion Detection is a technology that analyzes vocal characteristics and patterns in audio recordings to identify and classify the emotional state of the speaker.
InputType: audio OutputType: label
class TextSummarizationInputs
method __init__
__init__(node=None)
class TextSummarizationOutputs
method __init__
__init__(node=None)
class TextSummarization
Text summarization is the process of condensing a large body of text into a shorter version, capturing the main points and essential information while maintaining coherence and meaning.
InputType: text OutputType: text
class EntityLinkingInputs
method __init__
__init__(node=None)
class EntityLinkingOutputs
method __init__
__init__(node=None)
class EntityLinking
Entity Linking is the process of identifying and connecting mentions of entities within a text to their corresponding entries in a structured knowledge base, thereby enabling the disambiguation of terms and enhancing the understanding of the text's context.
InputType: text OutputType: label
class TextGenerationMetricInputs
method __init__
__init__(node=None)
class TextGenerationMetricOutputs
method __init__
__init__(node=None)
class TextGenerationMetric
A Text Generation Metric is a quantitative measure used to evaluate the quality and effectiveness of text produced by natural language processing models, often assessing aspects such as coherence, relevance, fluency, and adherence to given prompts or instructions.
InputType: text OutputType: text
class SplitOnLinebreakInputs
method __init__
__init__(node=None)
class SplitOnLinebreakOutputs
method __init__
__init__(node=None)
class SplitOnLinebreak
The "Split On Linebreak" function divides a given string into a list of substrings, using linebreaks (newline characters) as the points of separation.
InputType: text OutputType: text
class SentimentAnalysisInputs
method __init__
__init__(node=None)
class SentimentAnalysisOutputs
method __init__
__init__(node=None)
class SentimentAnalysis
Sentiment Analysis is a natural language processing technique used to determine and classify the emotional tone or subjective information expressed in a piece of text, such as identifying whether the sentiment is positive, negative, or neutral.
InputType: text OutputType: label
class KeywordSpottingInputs
method __init__
__init__(node=None)
class KeywordSpottingOutputs
method __init__
__init__(node=None)
class KeywordSpotting
Keyword Spotting is a function that enables the detection and identification of specific words or phrases within a stream of audio, often used in voice- activated systems to trigger actions or commands based on recognized keywords.
InputType: audio OutputType: label
class TextClassificationInputs
method __init__
__init__(node=None)
class TextClassificationOutputs
method __init__
__init__(node=None)
class TextClassification
Text Classification is a natural language processing task that involves categorizing text into predefined labels or classes based on its content, enabling automated organization, filtering, and analysis of large volumes of textual data.
InputType: text OutputType: label
class OtherMultipurposeInputs
method __init__
__init__(node=None)
class OtherMultipurposeOutputs
method __init__
__init__(node=None)
class OtherMultipurpose
The "Other (Multipurpose)" function serves as a versatile category designed to accommodate a wide range of tasks and activities that do not fit neatly into predefined classifications, offering flexibility and adaptability for various needs.
InputType: text OutputType: text
class SpeechSynthesisInputs
method __init__
__init__(node=None)
class SpeechSynthesisOutputs
method __init__
__init__(node=None)
class SpeechSynthesis
Speech synthesis is the artificial production of human speech, typically achieved through software or hardware systems that convert text into spoken words, enabling machines to communicate verbally with users.
InputType: text OutputType: audio
class AudioIntentDetectionInputs
method __init__
__init__(node=None)
class AudioIntentDetectionOutputs
method __init__
__init__(node=None)
class AudioIntentDetection
Audio Intent Detection is a process that involves analyzing audio signals to identify and interpret the underlying intentions or purposes behind spoken words, enabling systems to understand and respond appropriately to human speech.
InputType: audio OutputType: label
class VideoLabelDetectionInputs
method __init__
__init__(node=None)
class VideoLabelDetectionOutputs
method __init__
__init__(node=None)
class VideoLabelDetection
Video Label Detection is a function that automatically identifies and tags various objects, scenes, activities, and other relevant elements within a video, providing descriptive labels that enhance searchability and content organization.
InputType: video OutputType: label
class AsrQualityEstimationInputs
method __init__
__init__(node=None)
class AsrQualityEstimationOutputs
method __init__
__init__(node=None)
class AsrQualityEstimation
ASR Quality Estimation is a process that evaluates the accuracy and reliability of automatic speech recognition systems by analyzing their performance in transcribing spoken language into text.
InputType: text OutputType: label
class AudioTranscriptAnalysisInputs
method __init__
__init__(node=None)
class AudioTranscriptAnalysisOutputs
method __init__
__init__(node=None)
class AudioTranscriptAnalysis
Audio Transcript Analysis is a process that involves converting spoken language from audio recordings into written text, followed by examining and interpreting the transcribed content to extract meaningful insights, identify patterns, and derive actionable information.
InputType: audio OutputType: text
class SearchInputs
method __init__
__init__(node=None)
class SearchOutputs
method __init__
__init__(node=None)
class Search
The "Search" function allows users to input keywords or phrases to quickly locate specific information, files, or content within a database, website, or application.
InputType: text OutputType: text
class VideoForcedAlignmentInputs
method __init__
__init__(node=None)
class VideoForcedAlignmentOutputs
method __init__
__init__(node=None)
class VideoForcedAlignment
Video Forced Alignment is a process that synchronizes video footage with corresponding audio tracks by precisely aligning the visual and auditory elements, ensuring that the movements of speakers' lips match the spoken words.
InputType: video OutputType: video
class VisemeGenerationInputs
method __init__
__init__(node=None)
class VisemeGenerationOutputs
method __init__
__init__(node=None)
class VisemeGeneration
Viseme Generation is the process of creating visual representations of phonemes, which are the distinct units of sound in speech, to synchronize lip movements with spoken words in animations or virtual avatars.
InputType: text OutputType: label
class TopicClassificationInputs
method __init__
__init__(node=None)
class TopicClassificationOutputs
method __init__
__init__(node=None)
class TopicClassification
Topic Classification is a natural language processing function that categorizes text into predefined topics or subjects based on its content, enabling efficient organization and retrieval of information.
InputType: text OutputType: label
class OffensiveLanguageIdentificationInputs
method __init__
__init__(node=None)
class OffensiveLanguageIdentificationOutputs
method __init__
__init__(node=None)
class OffensiveLanguageIdentification
Offensive Language Identification is a function that analyzes text to detect and flag language that is abusive, harmful, or inappropriate, helping to maintain a respectful and safe communication environment.
InputType: text OutputType: label
class SpeechTranslationInputs
method __init__
__init__(node=None)
class SpeechTranslationOutputs
method __init__
__init__(node=None)
class SpeechTranslation
Speech Translation is a technology that converts spoken language in real-time from one language to another, enabling seamless communication between speakers of different languages.
InputType: audio OutputType: text
class SpeakerDiarizationAudioInputs
method __init__
__init__(node=None)
class SpeakerDiarizationAudioOutputs
method __init__
__init__(node=None)
class SpeakerDiarizationAudio
Speaker Diarization Audio is a process that involves segmenting an audio recording into distinct sections, each corresponding to a different speaker, in order to identify and differentiate between multiple speakers within the same audio stream.
InputType: audio OutputType: label
class AudioTranscriptImprovementInputs
method __init__
__init__(node=None)
class AudioTranscriptImprovementOutputs
method __init__
__init__(node=None)
class AudioTranscriptImprovement
Audio Transcript Improvement is a function that enhances the accuracy and clarity of transcribed audio recordings by correcting errors, refining language, and ensuring the text faithfully represents the original spoken content.
InputType: audio OutputType: text
class SpeechNonSpeechClassificationInputs
method __init__
__init__(node=None)
class SpeechNonSpeechClassificationOutputs
method __init__
__init__(node=None)
class SpeechNonSpeechClassification
The function "Speech or Non-Speech Classification" is designed to analyze audio input and determine whether the sound is human speech or non-speech noise, enabling applications such as voice recognition systems to filter out irrelevant background sounds.
InputType: audio OutputType: label
class TextDenormalizationInputs
method __init__
__init__(node=None)
class TextDenormalizationOutputs
method __init__
__init__(node=None)
class TextDenormalization
Text Denormalization is the process of converting abbreviated, contracted, or otherwise simplified text into its full, standard form, often to improve readability and ensure consistency in natural language processing tasks.
InputType: text OutputType: label
class ImageContentModerationInputs
method __init__
__init__(node=None)
class ImageContentModerationOutputs
method __init__
__init__(node=None)
class ImageContentModeration
Image Content Moderation is a process that involves analyzing and filtering images to detect and manage inappropriate, harmful, or sensitive content, ensuring compliance with community guidelines and legal standards.
InputType: image OutputType: label
class ReferencelessTextGenerationMetricDefaultInputs
method __init__
__init__(node=None)
class ReferencelessTextGenerationMetricDefaultOutputs
method __init__
__init__(node=None)
class ReferencelessTextGenerationMetricDefault
The Referenceless Text Generation Metric Default is a function designed to evaluate the quality of generated text without relying on reference texts for comparison.
InputType: text OutputType: text
class NamedEntityRecognitionInputs
method __init__
__init__(node=None)
class NamedEntityRecognitionOutputs
method __init__
__init__(node=None)
class NamedEntityRecognition
Named Entity Recognition (NER) is a natural language processing task that involves identifying and classifying proper nouns in text into predefined categories such as names of people, organizations, locations, dates, and other entities.
InputType: text OutputType: label
class TextContentModerationInputs
method __init__
__init__(node=None)
class TextContentModerationOutputs
method __init__
__init__(node=None)
class TextContentModeration
Text Content Moderation is the process of reviewing, filtering, and managing user-generated content to ensure it adheres to community guidelines, legal standards, and platform policies, thereby maintaining a safe and respectful online environment.
InputType: text OutputType: label
class SpeakerDiarizationVideoInputs
method __init__
__init__(node=None)
class SpeakerDiarizationVideoOutputs
method __init__
__init__(node=None)
class SpeakerDiarizationVideo
The Speaker Diarization Video function identifies and segments different speakers in a video, attributing portions of the audio to individual speakers to facilitate analysis and understanding of multi-speaker conversations.
InputType: video OutputType: label
class SplitOnSilenceInputs
method __init__
__init__(node=None)
class SplitOnSilenceOutputs
method __init__
__init__(node=None)
class SplitOnSilence
The "Split On Silence" function divides an audio recording into separate segments based on periods of silence, allowing for easier editing and analysis of individual sections.
InputType: audio OutputType: audio
class EmotionDetectionInputs
method __init__
__init__(node=None)
class EmotionDetectionOutputs
method __init__
__init__(node=None)
class EmotionDetection
Emotion Detection is a process that involves analyzing text to identify and categorize the emotional states or sentiments expressed by individuals, such as happiness, sadness, anger, or fear.
InputType: text OutputType: label
class TextSpamDetectionInputs
method __init__
__init__(node=None)
class TextSpamDetectionOutputs
method __init__
__init__(node=None)
class TextSpamDetection
Text Spam Detection is a process that involves analyzing and identifying unsolicited or irrelevant messages within text communications, typically using algorithms and machine learning techniques to filter out spam and ensure the integrity of the communication platform.
InputType: text OutputType: label
class TranslationInputs
method __init__
__init__(node=None)
class TranslationOutputs
method __init__
__init__(node=None)
class Translation
Translation is the process of converting text from one language into an equivalent text in another language, preserving the original meaning and context.
InputType: text OutputType: text
class VoiceActivityDetectionInputs
method __init__
__init__(node=None)
class VoiceActivityDetectionOutputs
method __init__
__init__(node=None)
class VoiceActivityDetection
Voice Activity Detection (VAD) is a technology that identifies the presence or absence of human speech within an audio signal, enabling systems to distinguish between spoken words and background noise.
InputType: audio OutputType: audio
class SpeechEmbeddingInputs
method __init__
__init__(node=None)
class SpeechEmbeddingOutputs
method __init__
__init__(node=None)
class SpeechEmbedding
Speech Embedding is a process that transforms spoken language into a fixed- dimensional vector representation, capturing essential features and characteristics of the speech for tasks such as recognition, classification, and analysis.
InputType: audio OutputType: text
class SubtitlingTranslationInputs
method __init__
__init__(node=None)
class SubtitlingTranslationOutputs
method __init__
__init__(node=None)
class SubtitlingTranslation
Subtitling Translation is the process of converting spoken dialogue from one language into written text in another language, which is then displayed on- screen to aid viewers in understanding the content.
InputType: text OutputType: text
class TextGenerationInputs
method __init__
__init__(node=None)
class TextGenerationOutputs
method __init__
__init__(node=None)
class TextGeneration
Text Generation is a process in which artificial intelligence models, such as neural networks, produce coherent and contextually relevant text based on a given input or prompt, often mimicking human writing styles and patterns.
InputType: text OutputType: text
class VideoUnderstandingInputs
method __init__
__init__(node=None)
class VideoUnderstandingOutputs
method __init__
__init__(node=None)
class VideoUnderstanding
Video Understanding is the process of analyzing and interpreting video content to extract meaningful information, such as identifying objects, actions, events, and contextual relationships within the footage.
InputType: video OutputType: text
class TextToVideoGenerationInputs
method __init__
__init__(node=None)
class TextToVideoGenerationOutputs
method __init__
__init__(node=None)
class TextToVideoGeneration
Text To Video Generation is a process that converts written descriptions or scripts into dynamic, visual video content using advanced algorithms and artificial intelligence.
InputType: text OutputType: video
class TextNormalizationInputs
method __init__
__init__(node=None)
class TextNormalizationOutputs
method __init__
__init__(node=None)
class TextNormalization
Text normalization is the process of transforming text into a standard, consistent format by correcting spelling errors, converting all characters to a uniform case, removing punctuation, and expanding abbreviations to improve the text's readability and usability for further processing or analysis.
InputType: text OutputType: label
class SpeechRecognitionInputs
method __init__
__init__(node=None)
class SpeechRecognitionOutputs
method __init__
__init__(node=None)
class SpeechRecognition
Speech recognition is a technology that enables a computer or device to identify and process spoken language, converting it into text.
InputType: audio OutputType: text
class SubtitlingInputs
method __init__
__init__(node=None)
class SubtitlingOutputs
method __init__
__init__(node=None)
class Subtitling
Subtitling is the process of displaying written text on a screen to represent the spoken dialogue, narration, or other audio elements in a video, typically to aid viewers who are deaf or hard of hearing, or to provide translations for audiences who speak different languages.
InputType: audio OutputType: text
class ClassificationMetricInputs
method __init__
__init__(node=None)
class ClassificationMetricOutputs
method __init__
__init__(node=None)
class ClassificationMetric
A Classification Metric is a quantitative measure used to evaluate the quality and effectiveness of classification models.
InputType: text OutputType: text
class TextToImageGenerationInputs
method __init__
__init__(node=None)
class TextToImageGenerationOutputs
method __init__
__init__(node=None)
class TextToImageGeneration
Text To Image Generation is a process where a system creates visual images based on descriptive text input, translating written language into corresponding graphical representations.
InputType: text OutputType: image
class Pipeline
method asr_age_classification
asr_age_classification(
asset_id: Union[str, Asset],
*args,
**kwargs
) → AsrAgeClassification
The ASR Age Classification function is designed to analyze audio recordings of speech to determine the speaker's age group by leveraging automatic speech recognition (ASR) technology and machine learning algorithms.
method asr_gender_classification
asr_gender_classification(
asset_id: Union[str, Asset],
*args,
**kwargs
) → AsrGenderClassification
The ASR Gender Classification function analyzes audio recordings to determine and classify the speaker's gender based on their voice characteristics.
method asr_quality_estimation
asr_quality_estimation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → AsrQualityEstimation
ASR Quality Estimation is a process that evaluates the accuracy and reliability of automatic speech recognition systems by analyzing their performance in transcribing spoken language into text.
method audio_emotion_detection
audio_emotion_detection(
asset_id: Union[str, Asset],
*args,
**kwargs
) → AudioEmotionDetection
Audio Emotion Detection is a technology that analyzes vocal characteristics and patterns in audio recordings to identify and classify the emotional state of the speaker.
method audio_forced_alignment
audio_forced_alignment(
asset_id: Union[str, Asset],
*args,
**kwargs
) → AudioForcedAlignment
Audio Forced Alignment is a process that synchronizes a given audio recording with its corresponding transcript by precisely aligning each spoken word or phoneme to its exact timing within the audio.
method audio_generation_metric
audio_generation_metric(
asset_id: Union[str, Asset],
*args,
**kwargs
) → AudioGenerationMetric
The Audio Generation Metric is a quantitative measure used to evaluate the quality, accuracy, and overall performance of audio generated by artificial intelligence systems, often considering factors such as fidelity, intelligibility, and similarity to human-produced audio.
method audio_intent_detection
audio_intent_detection(
asset_id: Union[str, Asset],
*args,
**kwargs
) → AudioIntentDetection
Audio Intent Detection is a process that involves analyzing audio signals to identify and interpret the underlying intentions or purposes behind spoken words, enabling systems to understand and respond appropriately to human speech.
method audio_language_identification
audio_language_identification(
asset_id: Union[str, Asset],
*args,
**kwargs
) → AudioLanguageIdentification
Audio Language Identification is a process that involves analyzing an audio recording to determine the language being spoken.
method audio_reconstruction
audio_reconstruction(
asset_id: Union[str, Asset],
*args,
**kwargs
) → AudioReconstruction
Audio Reconstruction is the process of restoring or recreating audio signals from incomplete, damaged, or degraded recordings to achieve a high-quality, accurate representation of the original sound.
method audio_transcript_analysis
audio_transcript_analysis(
asset_id: Union[str, Asset],
*args,
**kwargs
) → AudioTranscriptAnalysis
Audio Transcript Analysis is a process that involves converting spoken language from audio recordings into written text, followed by examining and interpreting the transcribed content to extract meaningful insights, identify patterns, and derive actionable information.
method audio_transcript_improvement
audio_transcript_improvement(
asset_id: Union[str, Asset],
*args,
**kwargs
) → AudioTranscriptImprovement
Audio Transcript Improvement is a function that enhances the accuracy and clarity of transcribed audio recordings by correcting errors, refining language, and ensuring the text faithfully represents the original spoken content.
method base_model
base_model(asset_id: Union[str, Asset], *args, **kwargs) → BaseModel
The Base-Model function serves as a foundational framework designed to provide essential features and capabilities upon which more specialized or advanced models can be built and customized.
method benchmark_scoring_asr
benchmark_scoring_asr(
asset_id: Union[str, Asset],
*args,
**kwargs
) → BenchmarkScoringAsr
Benchmark Scoring ASR is a function that evaluates and compares the performance of automatic speech recognition systems by analyzing their accuracy, speed, and other relevant metrics against a standardized set of benchmarks.
method benchmark_scoring_mt
benchmark_scoring_mt(
asset_id: Union[str, Asset],
*args,
**kwargs
) → BenchmarkScoringMt
Benchmark Scoring MT is a function designed to evaluate and score machine translation systems by comparing their output against a set of predefined benchmarks, thereby assessing their accuracy and performance.
method classification_metric
classification_metric(
asset_id: Union[str, Asset],
*args,
**kwargs
) → ClassificationMetric
A Classification Metric is a quantitative measure used to evaluate the quality and effectiveness of classification models.
method depth_estimation
depth_estimation(asset_id: Union[str, Asset], *args, **kwargs) → DepthEstimation
Depth estimation is a computational process that determines the distance of objects from a viewpoint, typically using visual data from cameras or sensors to create a three-dimensional understanding of a scene.
method diacritization
diacritization(asset_id: Union[str, Asset], *args, **kwargs) → Diacritization
Diacritization is the process of adding diacritical marks to letters in a text to indicate pronunciation, stress, tone, or meaning, often used in languages such as Arabic, Hebrew, and Vietnamese to provide clarity and accuracy in written communication.
method dialect_detection
dialect_detection(
asset_id: Union[str, Asset],
*args,
**kwargs
) → DialectDetection
Dialect Detection is a function that identifies and classifies the specific regional or social variations of a language spoken or written by an individual, enabling the recognition of distinct linguistic patterns and nuances associated with different dialects.
method document_image_parsing
document_image_parsing(
asset_id: Union[str, Asset],
*args,
**kwargs
) → DocumentImageParsing
Document Image Parsing is the process of analyzing and converting scanned or photographed images of documents into structured, machine-readable formats by identifying and extracting text, layout, and other relevant information.
method document_information_extraction
document_information_extraction(
asset_id: Union[str, Asset],
*args,
**kwargs
) → DocumentInformationExtraction
Document Information Extraction is the process of automatically identifying, extracting, and structuring relevant data from unstructured or semi-structured documents, such as invoices, receipts, contracts, and forms, to facilitate easier data management and analysis.
method emotion_detection
emotion_detection(
asset_id: Union[str, Asset],
*args,
**kwargs
) → EmotionDetection
Emotion Detection is a process that involves analyzing text to identify and categorize the emotional states or sentiments expressed by individuals, such as happiness, sadness, anger, or fear.
method entity_linking
entity_linking(asset_id: Union[str, Asset], *args, **kwargs) → EntityLinking
Entity Linking is the process of identifying and connecting mentions of entities within a text to their corresponding entries in a structured knowledge base, thereby enabling the disambiguation of terms and enhancing the understanding of the text's context.
method extract_audio_from_video
extract_audio_from_video(
asset_id: Union[str, Asset],
*args,
**kwargs
) → ExtractAudioFromVideo
The "Extract Audio From Video" function allows users to separate and save the audio track from a video file, enabling them to obtain just the sound without the accompanying visual content.
method fact_checking
fact_checking(asset_id: Union[str, Asset], *args, **kwargs) → FactChecking
Fact Checking is the process of verifying the accuracy and truthfulness of information, statements, or claims by cross-referencing with reliable sources and evidence.
method fill_text_mask
fill_text_mask(asset_id: Union[str, Asset], *args, **kwargs) → FillTextMask
The "Fill Text Mask" function takes a text input with masked or placeholder characters and replaces those placeholders with specified or contextually appropriate characters to generate a complete and coherent text output.
method image_captioning
image_captioning(asset_id: Union[str, Asset], *args, **kwargs) → ImageCaptioning
Image Captioning is a process that involves generating a textual description of an image, typically using machine learning models to analyze the visual content and produce coherent and contextually relevant sentences that describe the objects, actions, and scenes depicted in the image.
method image_colorization
image_colorization(
asset_id: Union[str, Asset],
*args,
**kwargs
) → ImageColorization
Image colorization is a process that involves adding color to grayscale images, transforming them from black-and-white to full-color representations, often using advanced algorithms and machine learning techniques to predict and apply the appropriate hues and shades.
method image_compression
image_compression(
asset_id: Union[str, Asset],
*args,
**kwargs
) → ImageCompression
Image compression is a process that reduces the file size of an image by removing redundant or non-essential data, while maintaining an acceptable level of visual quality.
method image_content_moderation
image_content_moderation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → ImageContentModeration
Image Content Moderation is a process that involves analyzing and filtering images to detect and manage inappropriate, harmful, or sensitive content, ensuring compliance with community guidelines and legal standards.
method image_embedding
image_embedding(asset_id: Union[str, Asset], *args, **kwargs) → ImageEmbedding
Image Embedding is a process that transforms an image into a fixed-dimensional vector representation, capturing its essential features and enabling efficient comparison, retrieval, and analysis in various machine learning and computer vision tasks.
method image_impainting
image_impainting(asset_id: Union[str, Asset], *args, **kwargs) → ImageImpainting
Image inpainting is a process that involves filling in missing or damaged parts of an image in a way that is visually coherent and seamlessly blends with the surrounding areas, often using advanced algorithms and techniques to restore the image to its original or intended appearance.
method image_label_detection
image_label_detection(
asset_id: Union[str, Asset],
*args,
**kwargs
) → ImageLabelDetection
Image Label Detection is a function that automatically identifies and assigns descriptive tags or labels to objects, scenes, or elements within an image, enabling easier categorization, search, and analysis of visual content.
method image_manipulation
image_manipulation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → ImageManipulation
Image Manipulation refers to the process of altering or enhancing digital images using various techniques and tools to achieve desired visual effects, correct imperfections, or transform the image's appearance.
method image_to_video_generation
image_to_video_generation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → ImageToVideoGeneration
The Image To Video Generation function transforms a series of static images into a cohesive, dynamic video sequence, often incorporating transitions, effects, and synchronization with audio to create a visually engaging narrative.
method instance_segmentation
instance_segmentation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → InstanceSegmentation
Instance segmentation is a computer vision task that involves detecting and delineating each distinct object within an image, assigning a unique label and precise boundary to every individual instance of objects, even if they belong to the same category.
method intent_classification
intent_classification(
asset_id: Union[str, Asset],
*args,
**kwargs
) → IntentClassification
Intent Classification is a natural language processing task that involves analyzing and categorizing user text input to determine the underlying purpose or goal behind the communication, such as booking a flight, asking for weather information, or setting a reminder.
method inverse_text_normalization
inverse_text_normalization(
asset_id: Union[str, Asset],
*args,
**kwargs
) → InverseTextNormalization
Inverse Text Normalization is the process of converting spoken or written language in its normalized form, such as numbers, dates, and abbreviations, back into their original, more complex or detailed textual representations.
method keyword_spotting
keyword_spotting(asset_id: Union[str, Asset], *args, **kwargs) → KeywordSpotting
Keyword Spotting is a function that enables the detection and identification of specific words or phrases within a stream of audio, often used in voice- activated systems to trigger actions or commands based on recognized keywords.
method language_identification
language_identification(
asset_id: Union[str, Asset],
*args,
**kwargs
) → LanguageIdentification
Language Identification is the process of automatically determining the language in which a given piece of text is written.
method language_identification_audio
language_identification_audio(
asset_id: Union[str, Asset],
*args,
**kwargs
) → LanguageIdentificationAudio
The Language Identification Audio function analyzes audio input to determine and identify the language being spoken.
method loglikelihood
loglikelihood(asset_id: Union[str, Asset], *args, **kwargs) → Loglikelihood
The Log Likelihood function measures the probability of observing the given data under a specific statistical model by taking the natural logarithm of the likelihood function, thereby transforming the product of probabilities into a sum, which simplifies the process of optimization and parameter estimation.
method metric_aggregation
metric_aggregation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → MetricAggregation
Metric Aggregation is a function that computes and summarizes numerical data by applying statistical operations, such as averaging, summing, or finding the minimum and maximum values, to provide insights and facilitate analysis of large datasets.
method multi_class_image_classification
multi_class_image_classification(
asset_id: Union[str, Asset],
*args,
**kwargs
) → MultiClassImageClassification
Multi Class Image Classification is a machine learning task where an algorithm is trained to categorize images into one of several predefined classes or categories based on their visual content.
method multi_class_text_classification
multi_class_text_classification(
asset_id: Union[str, Asset],
*args,
**kwargs
) → MultiClassTextClassification
Multi Class Text Classification is a natural language processing task that involves categorizing a given text into one of several predefined classes or categories based on its content.
method multi_label_text_classification
multi_label_text_classification(
asset_id: Union[str, Asset],
*args,
**kwargs
) → MultiLabelTextClassification
Multi Label Text Classification is a natural language processing task where a given text is analyzed and assigned multiple relevant labels or categories from a predefined set, allowing for the text to belong to more than one category simultaneously.
method multilingual_speech_recognition
multilingual_speech_recognition(
asset_id: Union[str, Asset],
*args,
**kwargs
) → MultilingualSpeechRecognition
Multilingual Speech Recognition is a technology that enables the automatic transcription of spoken language into text across multiple languages, allowing for seamless communication and understanding in diverse linguistic contexts.
method named_entity_recognition
named_entity_recognition(
asset_id: Union[str, Asset],
*args,
**kwargs
) → NamedEntityRecognition
Named Entity Recognition (NER) is a natural language processing task that involves identifying and classifying proper nouns in text into predefined categories such as names of people, organizations, locations, dates, and other entities.
method noise_removal
noise_removal(asset_id: Union[str, Asset], *args, **kwargs) → NoiseRemoval
Noise Removal is a process that involves identifying and eliminating unwanted random variations or disturbances from an audio signal to enhance the clarity and quality of the underlying information.
method object_detection
object_detection(asset_id: Union[str, Asset], *args, **kwargs) → ObjectDetection
Object Detection is a computer vision technology that identifies and locates objects within an image, typically by drawing bounding boxes around the detected objects and classifying them into predefined categories.
method ocr
ocr(asset_id: Union[str, Asset], *args, **kwargs) → Ocr
OCR, or Optical Character Recognition, is a technology that converts different types of documents, such as scanned paper documents, PDFs, or images captured by a digital camera, into editable and searchable data by recognizing and extracting text from the images.
method offensive_language_identification
offensive_language_identification(
asset_id: Union[str, Asset],
*args,
**kwargs
) → OffensiveLanguageIdentification
Offensive Language Identification is a function that analyzes text to detect and flag language that is abusive, harmful, or inappropriate, helping to maintain a respectful and safe communication environment.
method other__multipurpose_
other__multipurpose_(
asset_id: Union[str, Asset],
*args,
**kwargs
) → OtherMultipurpose
The "Other (Multipurpose)" function serves as a versatile category designed to accommodate a wide range of tasks and activities that do not fit neatly into predefined classifications, offering flexibility and adaptability for various needs.
method part_of_speech_tagging
part_of_speech_tagging(
asset_id: Union[str, Asset],
*args,
**kwargs
) → PartOfSpeechTagging
Part of Speech Tagging is a natural language processing task that involves assigning each word in a sentence its corresponding part of speech, such as noun, verb, adjective, or adverb, based on its role and context within the sentence.
method referenceless_audio_generation_metric
referenceless_audio_generation_metric(
asset_id: Union[str, Asset],
*args,
**kwargs
) → ReferencelessAudioGenerationMetric
The Referenceless Audio Generation Metric is a tool designed to evaluate the quality of generated audio content without the need for a reference or original audio sample for comparison.
method referenceless_text_generation_metric
referenceless_text_generation_metric(
asset_id: Union[str, Asset],
*args,
**kwargs
) → ReferencelessTextGenerationMetric
The Referenceless Text Generation Metric is a method for evaluating the quality of generated text without requiring a reference text for comparison, often leveraging models or algorithms to assess coherence, relevance, and fluency based on intrinsic properties of the text itself.
method referenceless_text_generation_metric_default
referenceless_text_generation_metric_default(
asset_id: Union[str, Asset],
*args,
**kwargs
) → ReferencelessTextGenerationMetricDefault
The Referenceless Text Generation Metric Default is a function designed to evaluate the quality of generated text without relying on reference texts for comparison.
method script_execution
script_execution(asset_id: Union[str, Asset], *args, **kwargs) → ScriptExecution
Script Execution refers to the process of running a set of programmed instructions or code within a computing environment, enabling the automated performance of tasks, calculations, or operations as defined by the script.
method search
search(asset_id: Union[str, Asset], *args, **kwargs) → Search
The "Search" function allows users to input keywords or phrases to quickly locate specific information, files, or content within a database, website, or application.
method semantic_segmentation
semantic_segmentation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → SemanticSegmentation
Semantic segmentation is a computer vision process that involves classifying each pixel in an image into a predefined category, effectively partitioning the image into meaningful segments based on the objects or regions they represent.
method sentiment_analysis
sentiment_analysis(
asset_id: Union[str, Asset],
*args,
**kwargs
) → SentimentAnalysis
Sentiment Analysis is a natural language processing technique used to determine and classify the emotional tone or subjective information expressed in a piece of text, such as identifying whether the sentiment is positive, negative, or neutral.
method speaker_diarization_audio
speaker_diarization_audio(
asset_id: Union[str, Asset],
*args,
**kwargs
) → SpeakerDiarizationAudio
Speaker Diarization Audio is a process that involves segmenting an audio recording into distinct sections, each corresponding to a different speaker, in order to identify and differentiate between multiple speakers within the same audio stream.
method speaker_diarization_video
speaker_diarization_video(
asset_id: Union[str, Asset],
*args,
**kwargs
) → SpeakerDiarizationVideo
The Speaker Diarization Video function identifies and segments different speakers in a video, attributing portions of the audio to individual speakers to facilitate analysis and understanding of multi-speaker conversations.
method speech_classification
speech_classification(
asset_id: Union[str, Asset],
*args,
**kwargs
) → SpeechClassification
Speech Classification is a process that involves analyzing and categorizing spoken language into predefined categories or classes based on various features such as tone, pitch, and linguistic content.
method speech_embedding
speech_embedding(asset_id: Union[str, Asset], *args, **kwargs) → SpeechEmbedding
Speech Embedding is a process that transforms spoken language into a fixed- dimensional vector representation, capturing essential features and characteristics of the speech for tasks such as recognition, classification, and analysis.
method speech_non_speech_classification
speech_non_speech_classification(
asset_id: Union[str, Asset],
*args,
**kwargs
) → SpeechNonSpeechClassification
The function "Speech or Non-Speech Classification" is designed to analyze audio input and determine whether the sound is human speech or non-speech noise, enabling applications such as voice recognition systems to filter out irrelevant background sounds.
method speech_recognition
speech_recognition(
asset_id: Union[str, Asset],
*args,
**kwargs
) → SpeechRecognition
Speech recognition is a technology that enables a computer or device to identify and process spoken language, converting it into text.
method speech_synthesis
speech_synthesis(asset_id: Union[str, Asset], *args, **kwargs) → SpeechSynthesis
Speech synthesis is the artificial production of human speech, typically achieved through software or hardware systems that convert text into spoken words, enabling machines to communicate verbally with users.
method speech_translation
speech_translation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → SpeechTranslation
Speech Translation is a technology that converts spoken language in real-time from one language to another, enabling seamless communication between speakers of different languages.
method split_on_linebreak
split_on_linebreak(
asset_id: Union[str, Asset],
*args,
**kwargs
) → SplitOnLinebreak
The "Split On Linebreak" function divides a given string into a list of substrings, using linebreaks (newline characters) as the points of separation.
method split_on_silence
split_on_silence(asset_id: Union[str, Asset], *args, **kwargs) → SplitOnSilence
The "Split On Silence" function divides an audio recording into separate segments based on periods of silence, allowing for easier editing and analysis of individual sections.
method style_transfer
style_transfer(asset_id: Union[str, Asset], *args, **kwargs) → StyleTransfer
Style Transfer is a technique in artificial intelligence that applies the visual style of one image (such as the brushstrokes of a famous painting) to the content of another image, effectively blending the artistic elements of the first image with the subject matter of the second.
method subtitling
subtitling(asset_id: Union[str, Asset], *args, **kwargs) → Subtitling
Subtitling is the process of displaying written text on a screen to represent the spoken dialogue, narration, or other audio elements in a video, typically to aid viewers who are deaf or hard of hearing, or to provide translations for audiences who speak different languages.
method subtitling_translation
subtitling_translation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → SubtitlingTranslation
Subtitling Translation is the process of converting spoken dialogue from one language into written text in another language, which is then displayed on- screen to aid viewers in understanding the content.
method text_classification
text_classification(
asset_id: Union[str, Asset],
*args,
**kwargs
) → TextClassification
Text Classification is a natural language processing task that involves categorizing text into predefined labels or classes based on its content, enabling automated organization, filtering, and analysis of large volumes of textual data.
method text_content_moderation
text_content_moderation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → TextContentModeration
Text Content Moderation is the process of reviewing, filtering, and managing user-generated content to ensure it adheres to community guidelines, legal standards, and platform policies, thereby maintaining a safe and respectful online environment.
method text_denormalization
text_denormalization(
asset_id: Union[str, Asset],
*args,
**kwargs
) → TextDenormalization
Text Denormalization is the process of converting abbreviated, contracted, or otherwise simplified text into its full, standard form, often to improve readability and ensure consistency in natural language processing tasks.
method text_embedding
text_embedding(asset_id: Union[str, Asset], *args, **kwargs) → TextEmbedding
Text embedding is a process that converts text into numerical vectors, capturing the semantic meaning and contextual relationships of words or phrases, enabling machines to understand and analyze natural language more effectively.
method text_generation
text_generation(asset_id: Union[str, Asset], *args, **kwargs) → TextGeneration
Text Generation is a process in which artificial intelligence models, such as neural networks, produce coherent and contextually relevant text based on a given input or prompt, often mimicking human writing styles and patterns.
method text_generation_metric
text_generation_metric(
asset_id: Union[str, Asset],
*args,
**kwargs
) → TextGenerationMetric
A Text Generation Metric is a quantitative measure used to evaluate the quality and effectiveness of text produced by natural language processing models, often assessing aspects such as coherence, relevance, fluency, and adherence to given prompts or instructions.
method text_generation_metric_default
text_generation_metric_default(
asset_id: Union[str, Asset],
*args,
**kwargs
) → TextGenerationMetricDefault
The "Text Generation Metric Default" function provides a standard set of evaluation metrics for assessing the quality and performance of text generation models.
method text_normalization
text_normalization(
asset_id: Union[str, Asset],
*args,
**kwargs
) → TextNormalization
Text normalization is the process of transforming text into a standard, consistent format by correcting spelling errors, converting all characters to a uniform case, removing punctuation, and expanding abbreviations to improve the text's readability and usability for further processing or analysis.
method text_reconstruction
text_reconstruction(
asset_id: Union[str, Asset],
*args,
**kwargs
) → TextReconstruction
Text Reconstruction is a process that involves piecing together fragmented or incomplete text data to restore it to its original, coherent form.
method text_segmenation
text_segmenation(asset_id: Union[str, Asset], *args, **kwargs) → TextSegmenation
Text Segmentation is the process of dividing a continuous text into meaningful units, such as words, sentences, or topics, to facilitate easier analysis and understanding.
method text_spam_detection
text_spam_detection(
asset_id: Union[str, Asset],
*args,
**kwargs
) → TextSpamDetection
Text Spam Detection is a process that involves analyzing and identifying unsolicited or irrelevant messages within text communications, typically using algorithms and machine learning techniques to filter out spam and ensure the integrity of the communication platform.
method text_summarization
text_summarization(
asset_id: Union[str, Asset],
*args,
**kwargs
) → TextSummarization
Text summarization is the process of condensing a large body of text into a shorter version, capturing the main points and essential information while maintaining coherence and meaning.
method text_to_audio
text_to_audio(asset_id: Union[str, Asset], *args, **kwargs) → TextToAudio
The Text to Audio function converts written text into spoken words, allowing users to listen to the content instead of reading it.
method text_to_image_generation
text_to_image_generation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → TextToImageGeneration
Text To Image Generation is a process where a system creates visual images based on descriptive text input, translating written language into corresponding graphical representations.
method text_to_video_generation
text_to_video_generation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → TextToVideoGeneration
Text To Video Generation is a process that converts written descriptions or scripts into dynamic, visual video content using advanced algorithms and artificial intelligence.
method topic_classification
topic_classification(
asset_id: Union[str, Asset],
*args,
**kwargs
) → TopicClassification
Topic Classification is a natural language processing function that categorizes text into predefined topics or subjects based on its content, enabling efficient organization and retrieval of information.
method translation
translation(asset_id: Union[str, Asset], *args, **kwargs) → Translation
Translation is the process of converting text from one language into an equivalent text in another language, preserving the original meaning and context.
method video_content_moderation
video_content_moderation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → VideoContentModeration
Video Content Moderation is the process of reviewing, analyzing, and filtering video content to ensure it adheres to community guidelines, legal standards, and platform policies, thereby preventing the dissemination of inappropriate, harmful, or illegal material.
method video_embedding
video_embedding(asset_id: Union[str, Asset], *args, **kwargs) → VideoEmbedding
Video Embedding is a process that transforms video content into a fixed- dimensional vector representation, capturing essential features and patterns to facilitate tasks such as retrieval, classification, and recommendation.
method video_forced_alignment
video_forced_alignment(
asset_id: Union[str, Asset],
*args,
**kwargs
) → VideoForcedAlignment
Video Forced Alignment is a process that synchronizes video footage with corresponding audio tracks by precisely aligning the visual and auditory elements, ensuring that the movements of speakers' lips match the spoken words.
method video_generation
video_generation(asset_id: Union[str, Asset], *args, **kwargs) → VideoGeneration
Video Generation is the process of creating video content through automated or semi-automated means, often utilizing algorithms, artificial intelligence, or software tools to produce visual and audio elements that can range from simple animations to complex, realistic scenes.
method video_label_detection
video_label_detection(
asset_id: Union[str, Asset],
*args,
**kwargs
) → VideoLabelDetection
Video Label Detection is a function that automatically identifies and tags various objects, scenes, activities, and other relevant elements within a video, providing descriptive labels that enhance searchability and content organization.
method video_understanding
video_understanding(
asset_id: Union[str, Asset],
*args,
**kwargs
) → VideoUnderstanding
Video Understanding is the process of analyzing and interpreting video content to extract meaningful information, such as identifying objects, actions, events, and contextual relationships within the footage.
method viseme_generation
viseme_generation(
asset_id: Union[str, Asset],
*args,
**kwargs
) → VisemeGeneration
Viseme Generation is the process of creating visual representations of phonemes, which are the distinct units of sound in speech, to synchronize lip movements with spoken words in animations or virtual avatars.
method visual_question_answering
visual_question_answering(
asset_id: Union[str, Asset],
*args,
**kwargs
) → VisualQuestionAnswering
Visual Question Answering (VQA) is a task in artificial intelligence that involves analyzing an image and providing accurate, contextually relevant answers to questions posed about the visual content of that image.
method voice_activity_detection
voice_activity_detection(
asset_id: Union[str, Asset],
*args,
**kwargs
) → VoiceActivityDetection
Voice Activity Detection (VAD) is a technology that identifies the presence or absence of human speech within an audio signal, enabling systems to distinguish between spoken words and background noise.
method voice_cloning
voice_cloning(asset_id: Union[str, Asset], *args, **kwargs) → VoiceCloning
Voice cloning is a technology that uses artificial intelligence to create a digital replica of a person's voice, allowing for the generation of speech that mimics the tone, pitch, and speaking style of the original speaker.