@huggingface/tasks 0.13.0-test5 → 0.13.1-test

package/src/tasks/automatic-speech-recognition/inference.ts

@@ -1,160 +0,0 @@
-/**
- * Inference code generated from the JSON schema spec in ./spec
- *
- * Using src/scripts/inference-codegen
- */
-
-/**
- * Inputs for Automatic Speech Recognition inference
- */
-export interface AutomaticSpeechRecognitionInput {
-	/**
-	 * The input audio data as a base64-encoded string. If no `parameters` are provided, you can
-	 * also provide the audio data as a raw bytes payload.
-	 */
-	inputs: string;
-	/**
-	 * Additional inference parameters
-	 */
-	parameters?: AutomaticSpeechRecognitionParameters;
-	[property: string]: unknown;
-}
-
-/**
- * Additional inference parameters
- *
- * Additional inference parameters for Automatic Speech Recognition
- */
-export interface AutomaticSpeechRecognitionParameters {
-	/**
-	 * Parametrization of the text generation process
-	 */
-	generation_parameters?: GenerationParameters;
-	/**
-	 * Whether to output corresponding timestamps with the generated text
-	 */
-	return_timestamps?: boolean;
-	[property: string]: unknown;
-}
-
-/**
- * Parametrization of the text generation process
- *
- * Ad-hoc parametrization of the text generation process
- */
-export interface GenerationParameters {
-	/**
-	 * Whether to use sampling instead of greedy decoding when generating new tokens.
-	 */
-	do_sample?: boolean;
-	/**
-	 * Controls the stopping condition for beam-based methods.
-	 */
-	early_stopping?: EarlyStoppingUnion;
-	/**
-	 * If set to float strictly between 0 and 1, only tokens with a conditional probability
-	 * greater than epsilon_cutoff will be sampled. In the paper, suggested values range from
-	 * 3e-4 to 9e-4, depending on the size of the model. See [Truncation Sampling as Language
-	 * Model Desmoothing](https://hf.co/papers/2210.15191) for more details.
-	 */
-	epsilon_cutoff?: number;
-	/**
-	 * Eta sampling is a hybrid of locally typical sampling and epsilon sampling. If set to
-	 * float strictly between 0 and 1, a token is only considered if it is greater than either
-	 * eta_cutoff or sqrt(eta_cutoff) * exp(-entropy(softmax(next_token_logits))). The latter
-	 * term is intuitively the expected next token probability, scaled by sqrt(eta_cutoff). In
-	 * the paper, suggested values range from 3e-4 to 2e-3, depending on the size of the model.
-	 * See [Truncation Sampling as Language Model Desmoothing](https://hf.co/papers/2210.15191)
-	 * for more details.
-	 */
-	eta_cutoff?: number;
-	/**
-	 * The maximum length (in tokens) of the generated text, including the input.
-	 */
-	max_length?: number;
-	/**
-	 * The maximum number of tokens to generate. Takes precedence over max_length.
-	 */
-	max_new_tokens?: number;
-	/**
-	 * The minimum length (in tokens) of the generated text, including the input.
-	 */
-	min_length?: number;
-	/**
-	 * The minimum number of tokens to generate. Takes precedence over min_length.
-	 */
-	min_new_tokens?: number;
-	/**
-	 * Number of groups to divide num_beams into in order to ensure diversity among different
-	 * groups of beams. See [this paper](https://hf.co/papers/1610.02424) for more details.
-	 */
-	num_beam_groups?: number;
-	/**
-	 * Number of beams to use for beam search.
-	 */
-	num_beams?: number;
-	/**
-	 * The value balances the model confidence and the degeneration penalty in contrastive
-	 * search decoding.
-	 */
-	penalty_alpha?: number;
-	/**
-	 * The value used to modulate the next token probabilities.
-	 */
-	temperature?: number;
-	/**
-	 * The number of highest probability vocabulary tokens to keep for top-k-filtering.
-	 */
-	top_k?: number;
-	/**
-	 * If set to float < 1, only the smallest set of most probable tokens with probabilities
-	 * that add up to top_p or higher are kept for generation.
-	 */
-	top_p?: number;
-	/**
-	 * Local typicality measures how similar the conditional probability of predicting a target
-	 * token next is to the expected conditional probability of predicting a random token next,
-	 * given the partial text already generated. If set to float < 1, the smallest set of the
-	 * most locally typical tokens with probabilities that add up to typical_p or higher are
-	 * kept for generation. See [this paper](https://hf.co/papers/2202.00666) for more details.
-	 */
-	typical_p?: number;
-	/**
-	 * Whether the model should use the past last key/values attentions to speed up decoding
-	 */
-	use_cache?: boolean;
-	[property: string]: unknown;
-}
-
-/**
- * Controls the stopping condition for beam-based methods.
- */
-export type EarlyStoppingUnion = boolean | "never";
-
-/**
- * Outputs of inference for the Automatic Speech Recognition task
- */
-export interface AutomaticSpeechRecognitionOutput {
-	/**
-	 * When returnTimestamps is enabled, chunks contains a list of audio chunks identified by
-	 * the model.
-	 */
-	chunks?: AutomaticSpeechRecognitionOutputChunk[];
-	/**
-	 * The recognized text.
-	 */
-	text: string;
-	[property: string]: unknown;
-}
-
-export interface AutomaticSpeechRecognitionOutputChunk {
-	/**
-	 * A chunk of text identified by the model
-	 */
-	text: string;
-	/**
-	 * The start and end timestamps corresponding with the text
-	 */
-	timestamps: number[];
-	[property: string]: unknown;
-}

package/src/tasks/automatic-speech-recognition/spec/input.json

@@ -1,35 +0,0 @@
-{
-	"$id": "/inference/schemas/automatic-speech-recognition/input.json",
-	"$schema": "http://json-schema.org/draft-06/schema#",
-	"description": "Inputs for Automatic Speech Recognition inference",
-	"title": "AutomaticSpeechRecognitionInput",
-	"type": "object",
-	"properties": {
-		"inputs": {
-			"description": "The input audio data as a base64-encoded string. If no `parameters` are provided, you can also provide the audio data as a raw bytes payload.",
-			"type": "string"
-		},
-		"parameters": {
-			"description": "Additional inference parameters",
-			"$ref": "#/$defs/AutomaticSpeechRecognitionParameters"
-		}
-	},
-	"$defs": {
-		"AutomaticSpeechRecognitionParameters": {
-			"title": "AutomaticSpeechRecognitionParameters",
-			"description": "Additional inference parameters for Automatic Speech Recognition",
-			"type": "object",
-			"properties": {
-				"return_timestamps": {
-					"type": "boolean",
-					"description": "Whether to output corresponding timestamps with the generated text"
-				},
-				"generation_parameters": {
-					"description": "Parametrization of the text generation process",
-					"$ref": "/inference/schemas/common-definitions.json#/definitions/GenerationParameters"
-				}
-			}
-		}
-	},
-	"required": ["inputs"]
-}

package/src/tasks/automatic-speech-recognition/spec/output.json

@@ -1,38 +0,0 @@
-{
-	"$id": "/inference/schemas/automatic-speech-recognition/output.json",
-	"$schema": "http://json-schema.org/draft-06/schema#",
-	"description": "Outputs of inference for the Automatic Speech Recognition task",
-	"title": "AutomaticSpeechRecognitionOutput",
-	"type": "object",
-	"properties": {
-		"text": {
-			"type": "string",
-			"description": "The recognized text."
-		},
-		"chunks": {
-			"type": "array",
-			"description": "When returnTimestamps is enabled, chunks contains a list of audio chunks identified by the model.",
-			"items": {
-				"type": "object",
-				"title": "AutomaticSpeechRecognitionOutputChunk",
-				"properties": {
-					"text": {
-						"type": "string",
-						"description": "A chunk of text identified by the model"
-					},
-					"timestamps": {
-						"type": "array",
-						"description": "The start and end timestamps corresponding with the text",
-						"items": {
-							"type": "number"
-						},
-						"minLength": 2,
-						"maxLength": 2
-					}
-				},
-				"required": ["text", "timestamps"]
-			}
-		}
-	},
-	"required": ["text"]
-}

package/src/tasks/chat-completion/inference.ts

@@ -1,322 +0,0 @@
-/**
- * Inference code generated from the JSON schema spec in ./spec
- *
- * Using src/scripts/inference-codegen
- */
-
-/**
- * Chat Completion Input.
- *
- * Auto-generated from TGI specs.
- * For more details, check out
- * https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.
- */
-export interface ChatCompletionInput {
-	/**
-	 * Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing
-	 * frequency in the text so far,
-	 * decreasing the model's likelihood to repeat the same line verbatim.
-	 */
-	frequency_penalty?: number;
-	/**
-	 * UNUSED
-	 * Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON
-	 * object that maps tokens
-	 * (specified by their token ID in the tokenizer) to an associated bias value from -100 to
-	 * 100. Mathematically,
-	 * the bias is added to the logits generated by the model prior to sampling. The exact
-	 * effect will vary per model,
-	 * but values between -1 and 1 should decrease or increase likelihood of selection; values
-	 * like -100 or 100 should
-	 * result in a ban or exclusive selection of the relevant token.
-	 */
-	logit_bias?: number[];
-	/**
-	 * Whether to return log probabilities of the output tokens or not. If true, returns the log
-	 * probabilities of each
-	 * output token returned in the content of message.
-	 */
-	logprobs?: boolean;
-	/**
-	 * The maximum number of tokens that can be generated in the chat completion.
-	 */
-	max_tokens?: number;
-	/**
-	 * A list of messages comprising the conversation so far.
-	 */
-	messages: ChatCompletionInputMessage[];
-	/**
-	 * [UNUSED] ID of the model to use. See the model endpoint compatibility table for details
-	 * on which models work with the Chat API.
-	 */
-	model?: string;
-	/**
-	 * UNUSED
-	 * How many chat completion choices to generate for each input message. Note that you will
-	 * be charged based on the
-	 * number of generated tokens across all of the choices. Keep n as 1 to minimize costs.
-	 */
-	n?: number;
-	/**
-	 * Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they
-	 * appear in the text so far,
-	 * increasing the model's likelihood to talk about new topics
-	 */
-	presence_penalty?: number;
-	response_format?: ChatCompletionInputGrammarType;
-	seed?: number;
-	/**
-	 * Up to 4 sequences where the API will stop generating further tokens.
-	 */
-	stop?: string[];
-	stream?: boolean;
-	stream_options?: ChatCompletionInputStreamOptions;
-	/**
-	 * What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the
-	 * output more random, while
-	 * lower values like 0.2 will make it more focused and deterministic.
-	 *
-	 * We generally recommend altering this or `top_p` but not both.
-	 */
-	temperature?: number;
-	tool_choice?: ChatCompletionInputTool;
-	/**
-	 * A prompt to be appended before the tools
-	 */
-	tool_prompt?: string;
-	/**
-	 * A list of tools the model may call. Currently, only functions are supported as a tool.
-	 * Use this to provide a list of
-	 * functions the model may generate JSON inputs for.
-	 */
-	tools?: ToolElement[];
-	/**
-	 * An integer between 0 and 5 specifying the number of most likely tokens to return at each
-	 * token position, each with
-	 * an associated log probability. logprobs must be set to true if this parameter is used.
-	 */
-	top_logprobs?: number;
-	/**
-	 * An alternative to sampling with temperature, called nucleus sampling, where the model
-	 * considers the results of the
-	 * tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10%
-	 * probability mass are considered.
-	 */
-	top_p?: number;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionInputMessage {
-	content: ChatCompletionInputMessageContent;
-	name?: string;
-	role: string;
-	[property: string]: unknown;
-}
-
-export type ChatCompletionInputMessageContent = ChatCompletionInputMessageChunk[] | string;
-
-export interface ChatCompletionInputMessageChunk {
-	image_url?: ChatCompletionInputURL;
-	text?: string;
-	type: ChatCompletionInputMessageChunkType;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionInputURL {
-	url: string;
-	[property: string]: unknown;
-}
-
-export type ChatCompletionInputMessageChunkType = "text" | "image_url";
-
-export interface ChatCompletionInputGrammarType {
-	type: ChatCompletionInputGrammarTypeType;
-	/**
-	 * A string that represents a [JSON Schema](https://json-schema.org/).
-	 *
-	 * JSON Schema is a declarative language that allows to annotate JSON documents
-	 * with types and descriptions.
-	 */
-	value: unknown;
-	[property: string]: unknown;
-}
-
-export type ChatCompletionInputGrammarTypeType = "json" | "regex";
-
-export interface ChatCompletionInputStreamOptions {
-	/**
-	 * If set, an additional chunk will be streamed before the data: [DONE] message. The usage
-	 * field on this chunk shows the token usage statistics for the entire request, and the
-	 * choices field will always be an empty array. All other chunks will also include a usage
-	 * field, but with a null value.
-	 */
-	include_usage: boolean;
-	[property: string]: unknown;
-}
-
-export type ChatCompletionInputTool = ChatCompletionInputToolType | string;
-
-export interface ChatCompletionInputToolType {
-	function?: ChatCompletionInputFunctionName;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionInputFunctionName {
-	name: string;
-	[property: string]: unknown;
-}
-
-export interface ToolElement {
-	function: ChatCompletionInputFunctionDefinition;
-	type: string;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionInputFunctionDefinition {
-	arguments: unknown;
-	description?: string;
-	name: string;
-	[property: string]: unknown;
-}
-
-/**
- * Chat Completion Output.
- *
- * Auto-generated from TGI specs.
- * For more details, check out
- * https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.
- */
-export interface ChatCompletionOutput {
-	choices: ChatCompletionOutputComplete[];
-	created: number;
-	id: string;
-	model: string;
-	system_fingerprint: string;
-	usage: ChatCompletionOutputUsage;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionOutputComplete {
-	finish_reason: string;
-	index: number;
-	logprobs?: ChatCompletionOutputLogprobs;
-	message: ChatCompletionOutputMessage;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionOutputLogprobs {
-	content: ChatCompletionOutputLogprob[];
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionOutputLogprob {
-	logprob: number;
-	token: string;
-	top_logprobs: ChatCompletionOutputTopLogprob[];
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionOutputTopLogprob {
-	logprob: number;
-	token: string;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionOutputMessage {
-	content?: string;
-	role: string;
-	tool_calls?: ChatCompletionOutputToolCall[];
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionOutputToolCall {
-	function: ChatCompletionOutputFunctionDefinition;
-	id: string;
-	type: string;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionOutputFunctionDefinition {
-	arguments: unknown;
-	description?: string;
-	name: string;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionOutputUsage {
-	completion_tokens: number;
-	prompt_tokens: number;
-	total_tokens: number;
-	[property: string]: unknown;
-}
-
-/**
- * Chat Completion Stream Output.
- *
- * Auto-generated from TGI specs.
- * For more details, check out
- * https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tgi-import.ts.
- */
-export interface ChatCompletionStreamOutput {
-	choices: ChatCompletionStreamOutputChoice[];
-	created: number;
-	id: string;
-	model: string;
-	system_fingerprint: string;
-	usage?: ChatCompletionStreamOutputUsage;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionStreamOutputChoice {
-	delta: ChatCompletionStreamOutputDelta;
-	finish_reason?: string;
-	index: number;
-	logprobs?: ChatCompletionStreamOutputLogprobs;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionStreamOutputDelta {
-	content?: string;
-	role: string;
-	tool_calls?: ChatCompletionStreamOutputDeltaToolCall;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionStreamOutputDeltaToolCall {
-	function: ChatCompletionStreamOutputFunction;
-	id: string;
-	index: number;
-	type: string;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionStreamOutputFunction {
-	arguments: string;
-	name?: string;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionStreamOutputLogprobs {
-	content: ChatCompletionStreamOutputLogprob[];
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionStreamOutputLogprob {
-	logprob: number;
-	token: string;
-	top_logprobs: ChatCompletionStreamOutputTopLogprob[];
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionStreamOutputTopLogprob {
-	logprob: number;
-	token: string;
-	[property: string]: unknown;
-}
-
-export interface ChatCompletionStreamOutputUsage {
-	completion_tokens: number;
-	prompt_tokens: number;
-	total_tokens: number;
-	[property: string]: unknown;
-}