@huggingface/transformers 3.3.3 → 3.4.1

package/src/utils/video.js

@@ -0,0 +1,128 @@
+import { RawImage } from "./image.js";
+import { apis } from "../env.js";
+
+export class RawVideoFrame {
+
+    /**
+     * @param {RawImage} image
+     * @param {number} timestamp
+     */
+    constructor(image, timestamp) {
+        this.image = image;
+        this.timestamp = timestamp;
+    }
+}
+
+export class RawVideo {
+    /**
+     * @param {RawVideoFrame[]|RawImage[]} frames
+     * @param {number} duration
+     */
+    constructor(frames, duration) {
+        if (frames.length > 0 && frames[0] instanceof RawImage) {
+            // Assume uniform timestamps
+            frames = frames.map((image, i) => new RawVideoFrame(image, (i + 1) / (frames.length + 1) * duration));
+        }
+        this.frames = /** @type {RawVideoFrame[]} */ (frames);
+        this.duration = duration;
+    }
+
+    get width() {
+        return this.frames[0].image.width;
+    }
+    get height() {
+        return this.frames[0].image.height;
+    }
+
+    get fps() {
+        return this.frames.length / this.duration;
+    }
+}
+
+
+/**
+ * Loads a video.
+ *
+ * @param {string|Blob|HTMLVideoElement} src The video to process.
+ * @param {Object} [options] Optional parameters.
+ * @param {number} [options.num_frames=null] The number of frames to sample uniformly.
+ * @param {number} [options.fps=null] The number of frames to sample per second.
+ *
+ * @returns {Promise<RawVideo>} The loaded video.
+ */
+export async function load_video(src, { num_frames = null, fps = null } = {}) {
+    if (!apis.IS_BROWSER_ENV) {
+        throw new Error("`load_video` is currently only supported in browser environments.");
+    }
+
+    // TODO: Support efficiently loading all frames using the WebCodecs API.
+    // Specfically, https://developer.mozilla.org/en-US/docs/Web/API/VideoDecoder
+    if (num_frames == null && fps == null) {
+        throw new Error("Either num_frames or fps must be provided.");
+    }
+
+    const frames = [];
+
+    const video = document.createElement("video");
+    video.crossOrigin = "anonymous";
+    video.muted = true; // mute to allow autoplay and seeking
+
+    if (typeof src === 'string') {
+        video.src = src;
+    } else if (src instanceof Blob) {
+        video.src = URL.createObjectURL(src);
+    } else if (src instanceof HTMLVideoElement) {
+        video.src = src.src;
+    } else {
+        throw new Error("Invalid URL or video element provided.");
+    }
+    // Wait for metadata to load to obtain duration
+    await new Promise((resolve) => video.onloadedmetadata = resolve);
+
+    if (video.seekable.start(0) === video.seekable.end(0)) {
+        // Fallback: Download entire video if not seekable
+        const response = await fetch(video.src);
+        const blob = await response.blob();
+        video.src = URL.createObjectURL(blob);
+        await new Promise((resolve) => video.onloadedmetadata = resolve);
+    }
+
+    const duration = video.duration;
+
+    let count, step;
+    if (num_frames != null) {
+        count = num_frames;
+        step = num_frames === 1 ? 0 : duration / (num_frames - 1);
+    } else {
+        step = 1 / fps;
+        count = Math.floor(duration / step);
+    }
+
+    // Build an array of sample times based on num_frames or fps
+    let sampleTimes = [];
+    for (let i = 0; i < count; ++i) {
+        sampleTimes.push(num_frames === 1 ? duration / 2 : i * step);
+    }
+
+    const canvas = document.createElement("canvas");
+    canvas.width = video.videoWidth;
+    canvas.height = video.videoHeight;
+    const ctx = canvas.getContext("2d", { willReadFrequently: true });
+    for (const t of sampleTimes) {
+        video.currentTime = t;
+        await new Promise((resolve) => {
+            video.onseeked = resolve;
+        });
+        ctx.drawImage(video, 0, 0, canvas.width, canvas.height);
+        const imageData = ctx.getImageData(0, 0, canvas.width, canvas.height);
+        const frameData = new RawImage(imageData.data, canvas.width, canvas.height, 4);
+
+        const frame = new RawVideoFrame(frameData, t);
+        frames.push(frame);
+    }
+
+    // Clean up video element.
+    video.remove();
+
+    return new RawVideo(frames, duration);
+}

package/types/backends/onnx.d.ts

@@ -6,12 +6,12 @@
 export function deviceToExecutionProviders(device?: import("../utils/devices.js").DeviceType | "auto" | null): ONNXExecutionProviders[];
 /**
  * Create an ONNX inference session.
- * @param {Uint8Array} buffer The ONNX model buffer.
+ * @param {Uint8Array|string} buffer_or_path The ONNX model buffer or path.
  * @param {import('onnxruntime-common').InferenceSession.SessionOptions} session_options ONNX inference session options.
  * @param {Object} session_config ONNX inference session configuration.
  * @returns {Promise<import('onnxruntime-common').InferenceSession & { config: Object}>} The ONNX inference session.
  */
-export function createInferenceSession(buffer: Uint8Array, session_options: import("onnxruntime-common").InferenceSession.SessionOptions, session_config: any): Promise<import("onnxruntime-common").InferenceSession & {
+export function createInferenceSession(buffer_or_path: Uint8Array | string, session_options: import("onnxruntime-common").InferenceSession.SessionOptions, session_config: any): Promise<import("onnxruntime-common").InferenceSession & {
     config: any;
 }>;
 /**

package/types/backends/onnx.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"onnx.d.ts","sourceRoot":"","sources":["../../src/backends/onnx.js"],"names":[],"mappings":"AA0GA;;;;GAIG;AACH,oDAHW,OAAO,qBAAqB,EAAE,UAAU,GAAC,MAAM,GAAC,IAAI,GAClD,sBAAsB,EAAE,CAqBpC;AAWD;;;;;;GAMG;AACH,+CALW,UAAU,mBACV,OAAO,oBAAoB,EAAE,gBAAgB,CAAC,cAAc,wBAE1D,OAAO,CAAC,OAAO,oBAAoB,EAAE,gBAAgB,GAAG;IAAE,MAAM,MAAQ;CAAC,CAAC,CActF;AAED;;;;GAIG;AACH,gCAHW,GAAG,GACD,OAAO,CAInB;AA+BD;;;GAGG;AACH,+BAFa,OAAO,CAKnB;;qCAnLY,OAAO,oBAAoB,EAAE,gBAAgB,CAAC,uBAAuB"}
+{"version":3,"file":"onnx.d.ts","sourceRoot":"","sources":["../../src/backends/onnx.js"],"names":[],"mappings":"AA0GA;;;;GAIG;AACH,oDAHW,OAAO,qBAAqB,EAAE,UAAU,GAAC,MAAM,GAAC,IAAI,GAClD,sBAAsB,EAAE,CAqBpC;AAWD;;;;;;GAMG;AACH,uDALW,UAAU,GAAC,MAAM,mBACjB,OAAO,oBAAoB,EAAE,gBAAgB,CAAC,cAAc,wBAE1D,OAAO,CAAC,OAAO,oBAAoB,EAAE,gBAAgB,GAAG;IAAE,MAAM,MAAQ;CAAC,CAAC,CActF;AAED;;;;GAIG;AACH,gCAHW,GAAG,GACD,OAAO,CAInB;AA8BD;;;GAGG;AACH,+BAFa,OAAO,CAKnB;;qCAlLY,OAAO,oBAAoB,EAAE,gBAAgB,CAAC,uBAAuB"}

package/types/configs.d.ts

@@ -83,6 +83,6 @@ export type TransformersJSConfig = {
     /**
      * Whether to load the model using the external data format (used for models >= 2GB in size).
      */
-    use_external_data_format?: boolean | Record<string, boolean>;
+    use_external_data_format?: import("./utils/hub.js").ExternalData | Record<string, import("./utils/hub.js").ExternalData>;
 };
 //# sourceMappingURL=configs.d.ts.map

package/types/configs.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"configs.d.ts","sourceRoot":"","sources":["../src/configs.js"],"names":[],"mappings":"AAuPA;;;;GAIG;AACH,0CAHW,gBAAgB;;;IACd,MAAM,CAAC,MAAM,EAAE,MAAM,EAAE,CAAC,CA2EpC;AACD;;;GAGG;AACH;IAwBI;;;;;;;;OAQG;IACH,sDANW,MAAM,0EACN,iBAAiB,GAGf,OAAO,CAAC,gBAAgB,CAAC,CAqBrC;IArCD;;;OAGG;IACH,6BAGC;IAnBD,0BAA0B;IAC1B,YADW,MAAM,GAAC,IAAI,CACJ;IAElB,sBAAsB;IACtB,oBADW,OAAO,CACS;IAE3B,qBAAqB;IACrB,yBADW,MAAM,CACO;IAExB,mCAAmC;IACnC,0BADW,oBAAoB,CACN;IAQrB,uBAAkD;CAgCzD;AAED;;;;;GAKG;AACH;IArCI;;;;;;;;OAQG;IACH,sDANW,MAAM,0EACN,iBAAiB,GAGf,OAAO,CAAC,gBAAgB,CAAC,CAqBrC;CAcJ;gCAzWY,OAAO,gBAAgB,EAAE,iBAAiB;+BAI1C,OAAO,iBAAiB,EAAE,gBAAgB;2BAI1C,OAAO,iBAAiB,EAAE,YAAY;;;;;;;;qBAsWrC,OAAO,mBAAmB,EAAE,QAAQ,GAAC,MAAM,CAAC,OAAO,mBAAmB,EAAE,QAAQ,EAAE,OAAO,mBAAmB,EAAE,QAAQ,CAAC;;;;;;+BACvH,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC;;;;aAGtB,OAAO,oBAAoB,EAAE,UAAU;;;;YACvC,OAAO,mBAAmB,EAAE,QAAQ,GAAC,MAAM,CAAC,MAAM,EAAE,OAAO,mBAAmB,EAAE,QAAQ,CAAC;;;;+BACzF,OAAO,GAAC,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC"}
+{"version":3,"file":"configs.d.ts","sourceRoot":"","sources":["../src/configs.js"],"names":[],"mappings":"AA4PA;;;;GAIG;AACH,0CAHW,gBAAgB;;;IACd,MAAM,CAAC,MAAM,EAAE,MAAM,EAAE,CAAC,CA2EpC;AACD;;;GAGG;AACH;IAwBI;;;;;;;;OAQG;IACH,sDANW,MAAM,0EACN,iBAAiB,GAGf,OAAO,CAAC,gBAAgB,CAAC,CAqBrC;IArCD;;;OAGG;IACH,6BAGC;IAnBD,0BAA0B;IAC1B,YADW,MAAM,GAAC,IAAI,CACJ;IAElB,sBAAsB;IACtB,oBADW,OAAO,CACS;IAE3B,qBAAqB;IACrB,yBADW,MAAM,CACO;IAExB,mCAAmC;IACnC,0BADW,oBAAoB,CACN;IAQrB,uBAAkD;CAgCzD;AAED;;;;;GAKG;AACH;IArCI;;;;;;;;OAQG;IACH,sDANW,MAAM,0EACN,iBAAiB,GAGf,OAAO,CAAC,gBAAgB,CAAC,CAqBrC;CAcJ;gCA9WY,OAAO,gBAAgB,EAAE,iBAAiB;+BAI1C,OAAO,iBAAiB,EAAE,gBAAgB;2BAI1C,OAAO,iBAAiB,EAAE,YAAY;;;;;;;;qBA2WrC,OAAO,mBAAmB,EAAE,QAAQ,GAAC,MAAM,CAAC,OAAO,mBAAmB,EAAE,QAAQ,EAAE,OAAO,mBAAmB,EAAE,QAAQ,CAAC;;;;;;+BACvH,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC;;;;aAGtB,OAAO,oBAAoB,EAAE,UAAU;;;;YACvC,OAAO,mBAAmB,EAAE,QAAQ,GAAC,MAAM,CAAC,MAAM,EAAE,OAAO,mBAAmB,EAAE,QAAQ,CAAC;;;;+BACzF,OAAO,gBAAgB,EAAE,YAAY,GAAC,MAAM,CAAC,MAAM,EAAE,OAAO,gBAAgB,EAAE,YAAY,CAAC"}

package/types/generation/streamers.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"streamers.d.ts","sourceRoot":"","sources":["../../src/generation/streamers.js"],"names":[],"mappings":"AASA;IACI;;;OAGG;IACH,WAFW,MAAM,EAAE,EAAE,QAIpB;IAED;;OAEG;IACH,YAEC;CACJ;AAMD;;GAEG;AACH;IACI;;;;;;;;;OASG;IACH,uBARW,OAAO,kBAAkB,EAAE,mBAAmB,+GAEtD;QAA0B,WAAW,GAA7B,OAAO;QACW,mBAAmB,GAArC,OAAO;QAC0B,iBAAiB,GAAlD,CAAS,IAAM,EAAN,MAAM,KAAG,IAAI;QACa,uBAAuB,GAA1D,CAAS,IAAQ,EAAR,MAAM,EAAE,KAAG,IAAI;QACP,aAAa;KACxC,EAoBA;IAVG,0DAA0B;IAC1B,qBAA8B;IAC9B,oCAA0D;IAC1D,gCAfgB,MAAM,EAAE,KAAG,IAAI,CAeuB;IACtD,mBAAyE;IAGzE,mBAAqB;IACrB,kBAAkB;IAClB,gCAAkC;IA6DtC;;;;OAIG;IACH,wBAHW,MAAM,cACN,OAAO,QASjB;CACJ;AAED;;;;;;;GAOG;AACH;IACI;;;;;;;;;;;;OAYG;IACH,uBAZW,OAAO,kBAAkB,EAAE,gBAAgB,gKAEnD;QAA0B,WAAW,GAA7B,OAAO;QAC0B,iBAAiB,GAAlD,CAAS,IAAM,EAAN,MAAM,KAAG,IAAI;QACa,uBAAuB,GAA1D,CAAS,IAAQ,EAAR,MAAM,EAAE,KAAG,IAAI;QACS,cAAc,GAA/C,CAAS,IAAM,EAAN,MAAM,KAAG,IAAI;QACW,YAAY,GAA7C,CAAS,IAAM,EAAN,MAAM,KAAG,IAAI;QACK,WAAW,GAAtC,MAAY,IAAI;QACC,cAAc,GAA/B,MAAM;QACY,mBAAmB,GAArC,OAAO;QACU,aAAa;KACxC,EA4BA;IATG,wBAAgD;IAEhD,uBA3BgB,MAAM,KAAG,IAAI,CA2BO;IACpC,qBA3BgB,MAAM,KAAG,IAAI,CA2BG;IAChC,mBA3BmB,IAAI,CA2BO;IAE9B,uBAAoC;IAEpC,+BAAkC;CAiCzC"}
+{"version":3,"file":"streamers.d.ts","sourceRoot":"","sources":["../../src/generation/streamers.js"],"names":[],"mappings":"AASA;IACI;;;OAGG;IACH,WAFW,MAAM,EAAE,EAAE,QAIpB;IAED;;OAEG;IACH,YAEC;CACJ;AAMD;;GAEG;AACH;IACI;;;;;;;;;OASG;IACH,uBARW,OAAO,kBAAkB,EAAE,mBAAmB,+GAEtD;QAA0B,WAAW,GAA7B,OAAO;QACW,mBAAmB,GAArC,OAAO;QAC0B,iBAAiB,GAAlD,CAAS,IAAM,EAAN,MAAM,KAAG,IAAI;QACa,uBAAuB,GAA1D,CAAS,IAAQ,EAAR,MAAM,EAAE,KAAG,IAAI;QACP,aAAa;KACxC,EAoBA;IAVG,0DAA0B;IAC1B,qBAA8B;IAC9B,oCAA0D;IAC1D,gCAfgB,MAAM,EAAE,KAAG,IAAI,CAeuB;IACtD,mBAAyE;IAGzE,mBAAqB;IACrB,kBAAkB;IAClB,gCAAkC;IA8DtC;;;;OAIG;IACH,wBAHW,MAAM,cACN,OAAO,QASjB;CACJ;AAED;;;;;;;GAOG;AACH;IACI;;;;;;;;;;;;OAYG;IACH,uBAZW,OAAO,kBAAkB,EAAE,gBAAgB,gKAEnD;QAA0B,WAAW,GAA7B,OAAO;QAC0B,iBAAiB,GAAlD,CAAS,IAAM,EAAN,MAAM,KAAG,IAAI;QACa,uBAAuB,GAA1D,CAAS,IAAQ,EAAR,MAAM,EAAE,KAAG,IAAI;QACS,cAAc,GAA/C,CAAS,IAAM,EAAN,MAAM,KAAG,IAAI;QACW,YAAY,GAA7C,CAAS,IAAM,EAAN,MAAM,KAAG,IAAI;QACK,WAAW,GAAtC,MAAY,IAAI;QACC,cAAc,GAA/B,MAAM;QACY,mBAAmB,GAArC,OAAO;QACU,aAAa;KACxC,EA4BA;IATG,wBAAgD;IAEhD,uBA3BgB,MAAM,KAAG,IAAI,CA2BO;IACpC,qBA3BgB,MAAM,KAAG,IAAI,CA2BG;IAChC,mBA3BmB,IAAI,CA2BO;IAE9B,uBAAoC;IAEpC,+BAAkC;CAiCzC"}

package/types/models/dac/feature_extraction_dac.d.ts

@@ -0,0 +1,4 @@
+export class DacFeatureExtractor extends EncodecFeatureExtractor {
+}
+import { EncodecFeatureExtractor } from '../encodec/feature_extraction_encodec.js';
+//# sourceMappingURL=feature_extraction_dac.d.ts.map

package/types/models/dac/feature_extraction_dac.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"feature_extraction_dac.d.ts","sourceRoot":"","sources":["../../../src/models/dac/feature_extraction_dac.js"],"names":[],"mappings":"AAEA;CAAoE;wCAF5B,0CAA0C"}

package/types/models/encodec/feature_extraction_encodec.d.ts

@@ -0,0 +1,13 @@
+export class EncodecFeatureExtractor extends FeatureExtractor {
+    /**
+     * Asynchronously extracts input values from a given audio using the provided configuration.
+     * @param {Float32Array|Float64Array} audio The audio data as a Float32Array/Float64Array.
+     * @returns {Promise<{ input_values: Tensor; }>} The extracted input values.
+     */
+    _call(audio: Float32Array | Float64Array): Promise<{
+        input_values: Tensor;
+    }>;
+}
+import { FeatureExtractor } from '../../base/feature_extraction_utils.js';
+import { Tensor } from '../../utils/tensor.js';
+//# sourceMappingURL=feature_extraction_encodec.d.ts.map

package/types/models/encodec/feature_extraction_encodec.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"feature_extraction_encodec.d.ts","sourceRoot":"","sources":["../../../src/models/encodec/feature_extraction_encodec.js"],"names":[],"mappings":"AAIA;IACI;;;;OAIG;IACH,aAHW,YAAY,GAAC,YAAY,GACvB,OAAO,CAAC;QAAE,YAAY,EAAE,MAAM,CAAC;KAAE,CAAC,CAsB9C;CACJ;iCA/BuD,wCAAwC;uBACzE,uBAAuB"}

package/types/models/feature_extractors.d.ts

@@ -1,8 +1,11 @@
 export * from "./audio_spectrogram_transformer/feature_extraction_audio_spectrogram_transformer.js";
+export * from "./encodec/feature_extraction_encodec.js";
 export * from "./clap/feature_extraction_clap.js";
+export * from "./dac/feature_extraction_dac.js";
 export * from "./moonshine/feature_extraction_moonshine.js";
 export * from "./pyannote/feature_extraction_pyannote.js";
 export * from "./seamless_m4t/feature_extraction_seamless_m4t.js";
+export * from "./snac/feature_extraction_snac.js";
 export * from "./speecht5/feature_extraction_speecht5.js";
 export * from "./wav2vec2/feature_extraction_wav2vec2.js";
 export * from "./wespeaker/feature_extraction_wespeaker.js";

package/types/models/florence2/processing_florence2.d.ts

@@ -26,7 +26,7 @@ export class Florence2Processor extends Processor {
      * @param {[number, number]} image_size The size of the image. height x width.
      */
     post_process_generation(text: string, task: string, image_size: [number, number]): {
-        [x: string]: string | {
+        [task]: string | {
             [x: string]: any[];
             labels: any[];
         };

package/types/models/florence2/processing_florence2.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"processing_florence2.d.ts","sourceRoot":"","sources":["../../../src/models/florence2/processing_florence2.js"],"names":[],"mappings":"AAIA;IACI,6CAAsC;IACtC,wDAAiD;IAEjD,0CA0BC;IAdG,kCAAkC;IAClC,mCADW,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CAC2E;IAEzG,kCAAkC;IAClC,6BADW,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CAC+D;IAE7F,kCAAkC;IAClC,yBADW,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CACuD;IAErF;;;MAGC;IACD,qBAAwB;IAG5B;;;;OAIG;IACH,wBAHW,MAAM,GAAC,MAAM,EAAE,GACb,MAAM,EAAE,CA6BpB;IAED;;;;;OAKG;IACH,8BAJW,MAAM,QACN,MAAM,cACN,CAAC,MAAM,EAAE,MAAM,CAAC;;;;;MAsC1B;IAID,0DAaC;CACJ;0BAlIyB,gCAAgC;8BAE5B,qBAAqB;mCADhB,kCAAkC"}
+{"version":3,"file":"processing_florence2.d.ts","sourceRoot":"","sources":["../../../src/models/florence2/processing_florence2.js"],"names":[],"mappings":"AAIA;IACI,6CAAsC;IACtC,wDAAiD;IAEjD,0CA0BC;IAdG,kCAAkC;IAClC,mCADW,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CAC2E;IAEzG,kCAAkC;IAClC,6BADW,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CAC+D;IAE7F,kCAAkC;IAClC,yBADW,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CACuD;IAErF;;;MAGC;IACD,qBAAwB;IAG5B;;;;OAIG;IACH,wBAHW,MAAM,GAAC,MAAM,EAAE,GACb,MAAM,EAAE,CA6BpB;IAED;;;;;OAKG;IACH,8BAJW,MAAM,QACN,MAAM,cACN,CAAC,MAAM,EAAE,MAAM,CAAC;QAqCd,CAAC,IAAI,CAAC;;;UAAc;MAChC;IAID,0DAaC;CACJ;0BAlIyB,gCAAgC;8BAE5B,qBAAqB;mCADhB,kCAAkC"}

package/types/models/image_processors.d.ts

@@ -31,6 +31,7 @@ export * from "./rt_detr/image_processing_rt_detr.js";
 export * from "./sam/image_processing_sam.js";
 export * from "./segformer/image_processing_segformer.js";
 export * from "./siglip/image_processing_siglip.js";
+export * from "./smolvlm/image_processing_smolvlm.js";
 export * from "./swin2sr/image_processing_swin2sr.js";
 export * from "./vit/image_processing_vit.js";
 export * from "./vitmatte/image_processing_vitmatte.js";

package/types/models/processors.d.ts

@@ -11,7 +11,9 @@ export * from "./paligemma/processing_paligemma.js";
 export * from "./pyannote/processing_pyannote.js";
 export * from "./qwen2_vl/processing_qwen2_vl.js";
 export * from "./sam/processing_sam.js";
+export * from "./smolvlm/processing_smolvlm.js";
 export * from "./speecht5/processing_speecht5.js";
+export * from "./ultravox/processing_ultravox.js";
 export * from "./wav2vec2/processing_wav2vec2.js";
 export * from "./wav2vec2_with_lm/processing_wav2vec2_with_lm.js";
 export * from "./whisper/processing_whisper.js";

package/types/models/smolvlm/image_processing_smolvlm.d.ts

@@ -0,0 +1,2 @@
+export { Idefics3ImageProcessor as SmolVLMImageProcessor } from "../idefics3/image_processing_idefics3.js";
+//# sourceMappingURL=image_processing_smolvlm.d.ts.map

package/types/models/smolvlm/image_processing_smolvlm.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"image_processing_smolvlm.d.ts","sourceRoot":"","sources":["../../../src/models/smolvlm/image_processing_smolvlm.js"],"names":[],"mappings":""}

package/types/models/smolvlm/processing_smolvlm.d.ts

@@ -0,0 +1,2 @@
+export { Idefics3Processor as SmolVLMProcessor } from "../idefics3/processing_idefics3.js";
+//# sourceMappingURL=processing_smolvlm.d.ts.map

package/types/models/smolvlm/processing_smolvlm.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"processing_smolvlm.d.ts","sourceRoot":"","sources":["../../../src/models/smolvlm/processing_smolvlm.js"],"names":[],"mappings":""}

package/types/models/snac/feature_extraction_snac.d.ts

@@ -0,0 +1,4 @@
+export class SnacFeatureExtractor extends DacFeatureExtractor {
+}
+import { DacFeatureExtractor } from '../dac/feature_extraction_dac.js';
+//# sourceMappingURL=feature_extraction_snac.d.ts.map

package/types/models/snac/feature_extraction_snac.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"feature_extraction_snac.d.ts","sourceRoot":"","sources":["../../../src/models/snac/feature_extraction_snac.js"],"names":[],"mappings":"AAEA;CAAiE;oCAF7B,kCAAkC"}

package/types/models/ultravox/processing_ultravox.d.ts

@@ -0,0 +1,16 @@
+/**
+ * Represents a UltravoxProcessor that extracts features from an audio input.
+ */
+export class UltravoxProcessor extends Processor {
+    static tokenizer_class: typeof AutoTokenizer;
+    static feature_extractor_class: typeof AutoFeatureExtractor;
+    /**
+     * @param {string} text The text input to process.
+     * @param {Float32Array} audio The audio input to process.
+     */
+    _call(text: string, audio?: Float32Array, kwargs?: {}): Promise<any>;
+}
+import { Processor } from "../../base/processing_utils.js";
+import { AutoTokenizer } from "../../tokenizers.js";
+import { AutoFeatureExtractor } from "../auto/feature_extraction_auto.js";
+//# sourceMappingURL=processing_ultravox.d.ts.map

package/types/models/ultravox/processing_ultravox.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"processing_ultravox.d.ts","sourceRoot":"","sources":["../../../src/models/ultravox/processing_ultravox.js"],"names":[],"mappings":"AAIA;;GAEG;AACH;IACI,6CAAsC;IACtC,4DAAqD;IAGrD;;;OAGG;IACH,YAHW,MAAM,UACN,YAAY,6BAsCtB;CACJ;0BAnDyB,gCAAgC;8BAD5B,qBAAqB;qCADd,oCAAoC"}

package/types/models/whisper/common_whisper.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"common_whisper.d.ts","sourceRoot":"","sources":["../../../src/models/whisper/common_whisper.js"],"names":[],"mappings":"AA4HA;;;GAGG;AACH,mDAHW,MAAM,GACJ,MAAM,CAwBlB;AA7CD,qDAAmE;AAEnE,6DAeG"}
+{"version":3,"file":"common_whisper.d.ts","sourceRoot":"","sources":["../../../src/models/whisper/common_whisper.js"],"names":[],"mappings":"AA4HA;;;GAGG;AACH,mDAHW,MAAM,GACJ,MAAM,CA8BlB;AAnDD,qDAAmE;AAEnE,6DAeG"}

package/types/models/whisper/feature_extraction_whisper.d.ts

@@ -12,7 +12,9 @@ export class WhisperFeatureExtractor extends FeatureExtractor {
      * @param {Float32Array|Float64Array} audio The audio data as a Float32Array/Float64Array.
      * @returns {Promise<{ input_features: Tensor }>} A Promise resolving to an object containing the extracted input features as a Tensor.
      */
-    _call(audio: Float32Array | Float64Array): Promise<{
+    _call(audio: Float32Array | Float64Array, { max_length, }?: {
+        max_length?: any;
+    }): Promise<{
         input_features: Tensor;
     }>;
 }

package/types/models/whisper/feature_extraction_whisper.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"feature_extraction_whisper.d.ts","sourceRoot":"","sources":["../../../src/models/whisper/feature_extraction_whisper.js"],"names":[],"mappings":"AAKA;IAEI,yBAeC;IADG,sCAAwD;IAG5D;;;;OAIG;IACH,kCAHW,YAAY,GAAC,YAAY,GACvB,OAAO,CAAC,MAAM,CAAC,CA0B3B;IAED;;;;OAIG;IACH,aAHW,YAAY,GAAC,YAAY,GACvB,OAAO,CAAC;QAAE,cAAc,EAAE,MAAM,CAAA;KAAE,CAAC,CAwB/C;CACJ;iCAnFuD,wCAAwC;uBACzE,uBAAuB"}
+{"version":3,"file":"feature_extraction_whisper.d.ts","sourceRoot":"","sources":["../../../src/models/whisper/feature_extraction_whisper.js"],"names":[],"mappings":"AAKA;IAEI,yBAeC;IADG,sCAAwD;IAG5D;;;;OAIG;IACH,kCAHW,YAAY,GAAC,YAAY,GACvB,OAAO,CAAC,MAAM,CAAC,CA6B3B;IAED;;;;OAIG;IACH,aAHW,YAAY,GAAC,YAAY;;QACvB,OAAO,CAAC;QAAE,cAAc,EAAE,MAAM,CAAA;KAAE,CAAC,CA6B/C;CACJ;iCA3FuD,wCAAwC;uBACzE,uBAAuB"}

package/types/models.d.ts

@@ -35,8 +35,8 @@ export class PreTrainedModel extends PreTrainedModel_base {
     sessions: Record<string, any>;
     configs: Record<string, any>;
     can_generate: boolean;
-    _forward: typeof decoderForward;
-    _prepare_inputs_for_generation: typeof image_text_to_text_prepare_inputs_for_generation;
+    _forward: typeof decoderForward | typeof autoEncoderForward;
+    _prepare_inputs_for_generation: typeof multimodal_text_to_text_prepare_inputs_for_generation;
     /** @type {import('./configs.js').TransformersJSConfig} */
     custom_config: import("./configs.js").TransformersJSConfig;
     /**
@@ -180,6 +180,9 @@ export class PreTrainedModel extends PreTrainedModel_base {
     encode_text({ input_ids }: {
         input_ids: any;
     }): Promise<any>;
+    encode_audio({ audio_values }: {
+        audio_values: any;
+    }): Promise<any>;
 }
 export class ModelOutput {
 }
@@ -1204,6 +1207,8 @@ export class WhisperForConditionalGeneration extends WhisperPreTrainedModel {
         sequences: Tensor;
     }, alignment_heads: number[][], num_frames?: number, time_precision?: number): Tensor;
 }
+export class LiteWhisperForConditionalGeneration extends WhisperForConditionalGeneration {
+}
 export class MoonshinePreTrainedModel extends PreTrainedModel {
     requires_attention_mask: boolean;
 }
@@ -1283,7 +1288,7 @@ export class PaliGemmaForConditionalGeneration extends PaliGemmaPreTrainedModel
 export class Idefics3PreTrainedModel extends PreTrainedModel {
 }
 /**
- * The LLAVA model which consists of a vision backbone and a language model.
+ * The Idefics3 model which consists of a vision backbone and a language model.
  */
 export class Idefics3ForConditionalGeneration extends Idefics3PreTrainedModel {
     encode_image({ pixel_values, pixel_attention_mask }: {
@@ -1295,6 +1300,12 @@ export class Idefics3ForConditionalGeneration extends Idefics3PreTrainedModel {
         attention_mask: any;
     };
 }
+/**
+ * The SmolVLM Model with a language modeling head.
+ * It is made up a SigLIP vision encoder, with a language modeling head on top.
+ */
+export class SmolVLMForConditionalGeneration extends Idefics3ForConditionalGeneration {
+}
 export class Phi3VPreTrainedModel extends PreTrainedModel {
 }
 export class Phi3VForCausalLM extends Phi3VPreTrainedModel {
@@ -1741,6 +1752,18 @@ export class Gemma2Model extends Gemma2PreTrainedModel {
 }
 export class Gemma2ForCausalLM extends Gemma2PreTrainedModel {
 }
+/**
+ * The bare Gemma3 Model outputting raw hidden-states without any specific head on top.
+ */
+export class Gemma3PreTrainedModel extends PreTrainedModel {
+}
+/**
+ * The bare Gemma3 Model outputting raw hidden-states without any specific head on top.
+ */
+export class Gemma3Model extends Gemma3PreTrainedModel {
+}
+export class Gemma3ForCausalLM extends Gemma3PreTrainedModel {
+}
 export class OpenELMPreTrainedModel extends PreTrainedModel {
 }
 export class OpenELMModel extends OpenELMPreTrainedModel {
@@ -2173,6 +2196,8 @@ export class SwinForImageClassification extends SwinPreTrainedModel {
      */
     _call(model_inputs: any): Promise<SequenceClassifierOutput>;
 }
+export class SwinForSemanticSegmentation extends SwinPreTrainedModel {
+}
 export class Swin2SRPreTrainedModel extends PreTrainedModel {
 }
 /**
@@ -2283,6 +2308,14 @@ export class DepthProPreTrainedModel extends PreTrainedModel {
 }
 export class DepthProForDepthEstimation extends DepthProPreTrainedModel {
 }
+export class Metric3DPreTrainedModel extends PreTrainedModel {
+}
+export class Metric3DForDepthEstimation extends Metric3DPreTrainedModel {
+}
+export class Metric3Dv2PreTrainedModel extends PreTrainedModel {
+}
+export class Metric3Dv2ForDepthEstimation extends Metric3Dv2PreTrainedModel {
+}
 export class MaskFormerPreTrainedModel extends PreTrainedModel {
 }
 export class MaskFormerModel extends MaskFormerPreTrainedModel {
@@ -3446,6 +3479,8 @@ export class MobileNetV1ForImageClassification extends MobileNetV1PreTrainedMode
      */
     _call(model_inputs: any): Promise<SequenceClassifierOutput>;
 }
+export class MobileNetV1ForSemanticSegmentation extends MobileNetV1PreTrainedModel {
+}
 export class MobileNetV2PreTrainedModel extends PreTrainedModel {
 }
 /**
@@ -3463,6 +3498,8 @@ export class MobileNetV2ForImageClassification extends MobileNetV2PreTrainedMode
      */
     _call(model_inputs: any): Promise<SequenceClassifierOutput>;
 }
+export class MobileNetV2ForSemanticSegmentation extends MobileNetV2PreTrainedModel {
+}
 export class MobileNetV3PreTrainedModel extends PreTrainedModel {
 }
 /**
@@ -3480,6 +3517,8 @@ export class MobileNetV3ForImageClassification extends MobileNetV3PreTrainedMode
      */
     _call(model_inputs: any): Promise<SequenceClassifierOutput>;
 }
+export class MobileNetV3ForSemanticSegmentation extends MobileNetV3PreTrainedModel {
+}
 export class MobileNetV4PreTrainedModel extends PreTrainedModel {
 }
 /**
@@ -3497,6 +3536,8 @@ export class MobileNetV4ForImageClassification extends MobileNetV4PreTrainedMode
      */
     _call(model_inputs: any): Promise<SequenceClassifierOutput>;
 }
+export class MobileNetV4ForSemanticSegmentation extends MobileNetV4PreTrainedModel {
+}
 export class DecisionTransformerPreTrainedModel extends PreTrainedModel {
 }
 /**
@@ -3562,6 +3603,134 @@ export class PatchTSMixerModel extends PatchTSMixerPreTrainedModel {
  */
 export class PatchTSMixerForPrediction extends PatchTSMixerPreTrainedModel {
 }
+export class UltravoxPreTrainedModel extends PreTrainedModel {
+}
+export class UltravoxModel extends UltravoxPreTrainedModel {
+    _merge_input_ids_with_audio_features(kwargs: any): {
+        inputs_embeds: any;
+        attention_mask: any;
+    };
+}
+export class MimiPreTrainedModel extends PreTrainedModel {
+}
+export class MimiEncoderOutput extends ModelOutput {
+    /**
+     * @param {Object} output The output of the model.
+     * @param {Tensor} output.audio_codes Discrete code embeddings, of shape `(batch_size, num_quantizers, codes_length)`.
+     */
+    constructor({ audio_codes }: {
+        audio_codes: Tensor;
+    });
+    audio_codes: Tensor;
+}
+export class MimiDecoderOutput extends ModelOutput {
+    /**
+     * @param {Object} output The output of the model.
+     * @param {Tensor} output.audio_values Decoded audio values, of shape `(batch_size, num_channels, sequence_length)`.
+     */
+    constructor({ audio_values }: {
+        audio_values: Tensor;
+    });
+    audio_values: Tensor;
+}
+/**
+ * The Mimi neural audio codec model.
+ */
+export class MimiModel extends MimiPreTrainedModel {
+    /**
+     * Encodes the input audio waveform into discrete codes.
+     * @param {Object} inputs Model inputs
+     * @param {Tensor} [inputs.input_values] Float values of the input audio waveform, of shape `(batch_size, channels, sequence_length)`).
+     * @returns {Promise<MimiEncoderOutput>} The output tensor of shape `(batch_size, num_codebooks, sequence_length)`.
+     */
+    encode(inputs: {
+        input_values?: Tensor;
+    }): Promise<MimiEncoderOutput>;
+    /**
+     * Decodes the given frames into an output audio waveform.
+     * @param {MimiEncoderOutput} inputs The encoded audio codes.
+     * @returns {Promise<MimiDecoderOutput>} The output tensor of shape `(batch_size, num_channels, sequence_length)`.
+     */
+    decode(inputs: MimiEncoderOutput): Promise<MimiDecoderOutput>;
+}
+export class MimiEncoderModel extends MimiPreTrainedModel {
+}
+export class MimiDecoderModel extends MimiPreTrainedModel {
+}
+export class DacPreTrainedModel extends PreTrainedModel {
+}
+export class DacEncoderOutput extends ModelOutput {
+    /**
+     * @param {Object} output The output of the model.
+     * @param {Tensor} output.audio_codes Discrete code embeddings, of shape `(batch_size, num_quantizers, codes_length)`.
+     */
+    constructor({ audio_codes }: {
+        audio_codes: Tensor;
+    });
+    audio_codes: Tensor;
+}
+export class DacDecoderOutput extends ModelOutput {
+    /**
+     * @param {Object} output The output of the model.
+     * @param {Tensor} output.audio_values Decoded audio values, of shape `(batch_size, num_channels, sequence_length)`.
+     */
+    constructor({ audio_values }: {
+        audio_values: Tensor;
+    });
+    audio_values: Tensor;
+}
+/**
+ * The DAC (Descript Audio Codec) model.
+ */
+export class DacModel extends DacPreTrainedModel {
+    /**
+     * Encodes the input audio waveform into discrete codes.
+     * @param {Object} inputs Model inputs
+     * @param {Tensor} [inputs.input_values] Float values of the input audio waveform, of shape `(batch_size, channels, sequence_length)`).
+     * @returns {Promise<DacEncoderOutput>} The output tensor of shape `(batch_size, num_codebooks, sequence_length)`.
+     */
+    encode(inputs: {
+        input_values?: Tensor;
+    }): Promise<DacEncoderOutput>;
+    /**
+     * Decodes the given frames into an output audio waveform.
+     * @param {DacEncoderOutput} inputs The encoded audio codes.
+     * @returns {Promise<DacDecoderOutput>} The output tensor of shape `(batch_size, num_channels, sequence_length)`.
+     */
+    decode(inputs: DacEncoderOutput): Promise<DacDecoderOutput>;
+}
+export class DacEncoderModel extends DacPreTrainedModel {
+}
+export class DacDecoderModel extends DacPreTrainedModel {
+}
+export class SnacPreTrainedModel extends PreTrainedModel {
+}
+/**
+ * The SNAC (Multi-Scale Neural Audio Codec) model.
+ */
+export class SnacModel extends SnacPreTrainedModel {
+    /**
+     * Encodes the input audio waveform into discrete codes.
+     * @param {Object} inputs Model inputs
+     * @param {Tensor} [inputs.input_values] Float values of the input audio waveform, of shape `(batch_size, channels, sequence_length)`).
+     * @returns {Promise<Record<string, Tensor>>} The output tensors of shape `(batch_size, num_codebooks, sequence_length)`.
+     */
+    encode(inputs: {
+        input_values?: Tensor;
+    }): Promise<Record<string, Tensor>>;
+    /**
+     * Decodes the given frames into an output audio waveform.
+     * @param {Record<string, Tensor>} inputs The encoded audio codes.
+     * @returns {Promise<{audio_values: Tensor}>} The output tensor of shape `(batch_size, num_channels, sequence_length)`.
+     */
+    decode(inputs: Record<string, Tensor>): Promise<{
+        audio_values: Tensor;
+    }>;
+}
+export class SnacEncoderModel extends SnacPreTrainedModel {
+}
+export class SnacDecoderModel extends SnacPreTrainedModel {
+}
 /**
  * Base class of all AutoModels. Contains the `from_pretrained` function
  * which is used to instantiate pretrained models.
@@ -3799,6 +3968,12 @@ export class AutoModelForPoseEstimation extends PretrainedMixin {
 export class AutoModelForImageFeatureExtraction extends PretrainedMixin {
     static MODEL_CLASS_MAPPINGS: Map<string, (string | typeof CLIPVisionModelWithProjection)[]>[];
 }
+export class AutoModelForImageTextToText extends PretrainedMixin {
+    static MODEL_CLASS_MAPPINGS: Map<string, (string | typeof Idefics3ForConditionalGeneration)[] | (string | typeof Florence2ForConditionalGeneration)[]>[];
+}
+export class AutoModelForAudioTextToText extends PretrainedMixin {
+    static MODEL_CLASS_MAPPINGS: Map<string, (string | typeof UltravoxModel)[]>[];
+}
 export class Seq2SeqLMOutput extends ModelOutput {
     /**
      * @param {Object} output The output of the model.
@@ -3961,7 +4136,8 @@ export class VitsModelOutput extends ModelOutput {
  * @private
  */
 declare function decoderForward(self: any, model_inputs: any, is_encoder_decoder?: boolean): Promise<any>;
-declare function image_text_to_text_prepare_inputs_for_generation(self: any, ...args: any[]): any;
+declare function autoEncoderForward(self: any, model_inputs: any): Promise<any>;
+declare function multimodal_text_to_text_prepare_inputs_for_generation(self: any, ...args: any[]): any;
 import { GenerationConfig } from './generation/configuration_utils.js';
 import { LogitsProcessorList } from './generation/logits_process.js';
 import { StoppingCriteriaList } from './generation/stopping_criteria.js';